Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are present, and the description fails to disclose any behavioral traits. It doesn't mention whether the comment is appended to existing comments, if permissions are required, or what the response/return value looks like. The description is purely declarative with no additional context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is concise and front-loaded, but it is minimal and provides no additional explanatory value. It is not overly verbose, but it lacks any structure or extra context that would make it more than a basic statement.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity, the description is still incomplete. It doesn't mention return values, relationship to list_vulnerability_comments, or any potential side effects. The agent would need to infer these from the schema or other tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully describes both parameters (vulnerability_id and content) with types and descriptions. The description adds no extra meaning beyond the schema, but since schema coverage is 100%, the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (add) and the resource (comment to a vulnerability). It distinguishes from siblings like update_vulnerability and list_vulnerability_comments by the explicit 'add' operation. However, it doesn't elaborate on what constitutes a comment or any nuances.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. There is no mention of related tools like list_vulnerability_comments or any prerequisites for adding a comment. The description only states the action without context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description must disclose behavioral traits, but it only states the action generically. It does not mention side effects, prerequisites, whether it modifies existing scan configurations, or how the regex parameters interact with detection. This is insufficient for a mutation-like configuration tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, brief sentence with no wasted words, and the tool name is front-loaded in the description. However, it may be too terse to be genuinely helpful, lacking any contextual expansion.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has four parameters and no output schema or annotations, so the description should explain the purpose in more depth. It only describes the high-level goal without connecting to the scan config context or explaining how the configuration is applied. This is insufficient for safe and correct invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has descriptions for all four parameters, achieving 100% coverage, so the baseline is 3. The description adds no parameter-specific information, so it neither enhances nor detracts from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Configure') and a specific resource ('automatic CSRF token detection and injection'), making it clear what the tool addresses. However, it does not explicitly distinguish this from sibling configuration tools like configure_form_auth or configure_oauth, though the CSRF focus is evident from the name.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided about when to use this tool instead of alternatives such as configure_token_replacement or configure_session_handling. The description only states the function, leaving the agent to infer usage context from the name and schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden for behavioral disclosure. It only says 'Configure' without mentioning side effects, permission requirements, reversibility, validation behavior, or what happens to existing settings. This is inadequate for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the core action and resource. There is zero wasted wording, making it highly concise. It does not repeat schema information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has 8 parameters, 5 required, no output schema, and no annotations, the one-sentence description is insufficient. It fails to explain the configuration process, expected effects, prerequisites, or any behavioral caveats. The schema covers parameters but not the operational context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are already well-documented. The description adds no extra meaning beyond labeling the auth type as 'form-based', which the schema's username/password fields already imply. Baseline 3 is appropriate because the description does not enhance parameter understanding.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool configures form-based authentication (username/password login) for a scan configuration. This distinguishes it from sibling tools like configure_oauth and configure_macro_auth by naming the specific authentication type.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit guidance on when to use this tool versus alternatives such as configure_oauth or configure_token_replacement. The context of 'form-based authentication' implies usage but does not provide exclusions or decision criteria, especially given the many sibling authentication tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full responsibility for disclosing behavioral traits. It only says 'configure macro-based authentication' without explaining what changes occur (e.g., associating the macro with a scan config), whether the operation is reversible, or any side effects. The lack of detail about the configuration process or return behavior is a significant gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that starts with the action verb 'Configure' and introduces the key concept. It avoids unnecessary words and is well-structured, though it could include a bit more contextual detail without becoming overly verbose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the complexity of the tool (4 parameters, no annotations, no output schema), the description is notably incomplete. It fails to explain what macro-based authentication entails, how it integrates with scan configurations, or when it should be used. The sibling tools highlight the need for differentiation and contextual guidance, which is entirely absent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the parameters are fully documented in the schema. The description adds no meaningful information about the parameters beyond what the schema already provides (e.g., it doesn't mention replay_speed or extra_delay_ms). This aligns with the baseline score of 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies the verb 'configure' and the resource 'macro-based authentication', which clearly distinguishes it from sibling auth tools like configure_form_auth and configure_oauth. The phrase 'using a previously uploaded macro file' adds key context about the prerequisite, making the purpose clear and specific, though it doesn't explicitly mention that it applies to a scan configuration.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies a prerequisite (previously uploaded macro file) but provides no guidance on when to use this tool versus alternatives such as configure_form_auth or configure_oauth. It does not mention trade-offs, exclusions, or scenarios where macro-based auth is preferred, leaving the agent without context for tool selection.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'Configure' (implying a write operation) but does not mention prerequisites (e.g., scan config must exist), effects on existing OAuth settings, security implications (e.g., client secret storage), or idempotency. This is a significant gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no wasted words. It front-loads the primary action and resource, making it easy to parse and remember.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the moderate complexity (10 parameters, 5 required), no output schema, and lack of annotations, the description is too sparse to be fully self-contained. It does not explain what 'configure' entails, any required setup, or how this relates to other scan configuration tools, leaving important gaps for the agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with all ten parameters having descriptive names and descriptions. The tool description adds no parameter-specific detail, but the baseline of 3 is appropriate because the schema already provides full semantic coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Configure' and the resource 'OAuth 2.0 authentication for a scan configuration', which is specific and distinguishes this tool from sibling configure_* tools (e.g., configure_form_auth, configure_token_replacement). The purpose is unambiguous and well-scoped.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives. With multiple configure_* siblings, the absence of any comparative or conditional context (e.g., 'use when OAuth is required') means the agent must infer usage solely from the tool name and minimal description.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It states what the tool does but does not mention side effects, mutability, permissions required, or reversibility. As a configuration tool, it likely modifies an existing scan config, but the description does not reveal whether changes are immediately applied, if they can be undone, or what the response format is. This leaves the agent uncertain about the operation's safety and impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence that leads with the verb 'Configure' and states the main scope. There is no fluff or repetition. Every word contributes to understanding the tool's core function, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 6 parameters, no output schema, and no annotations. While the parameter schema is complete, the description does not provide contextual completeness for a configuration mutation: it lacks usage scenarios, behavioral implications, or any operational expectations. An agent using this tool would need more context to understand how it fits into the broader scan configuration workflow, especially given the many sibling configuration tools.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, meaning every parameter (lock_cookies, session_loss_regex, etc.) has a descriptive comment. The tool description itself adds no additional parameter context, but per the rubric, the baseline is 3 when the schema covers all parameters. The parameter descriptions are reasonably self-explanatory, so no significant gap exists.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Configure session management including cookie handling and automatic re-login on session loss.' It uses a specific verb ('Configure') and names the resource (session management) plus key capabilities. While it doesn't explicitly differentiate from sibling configuration tools like configure_form_auth or configure_oauth, the focus on session handling is distinctive enough to avoid serious ambiguity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided regarding when to use this tool versus alternatives. The description does not mention any prerequisites, exclusions, or compare itself to sibling tools. A user must infer from the name and context that this tool is for session-related configuration, but no explicit usage direction is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the burden of disclosing behavior. It explains the core extract/inject mechanism and the global scope, but does not disclose whether existing rules are overwritten, whether it is a mutating operation, or any side effects on ongoing scans. This is adequate but not fully transparent.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Two sentences with no redundant content. The first sentence states the purpose, the second gives concrete examples. Information is front-loaded and every word earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is complete enough for an agent to understand when to select the tool and what it does. It does not explain return values (no output schema) or whether configuration replaces existing rules, but for selection and basic understanding, it covers the essential context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description adds high-level context about token extraction/injection but does not elaborate on specific parameter usage beyond what the schema already provides. It neither adds nor detracts from the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Configure global token replacement rules to extract tokens from responses and inject them into subsequent requests.' This is a specific verb+resource+scope formulation that distinguishes it from sibling tools like configure_csrf_handling or configure_session_handling by focusing on token replacement.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The second sentence provides clear usage context: 'Use this for dynamic tokens like CSRF tokens, API keys, or session identifiers that need to be captured and replayed.' This indicates when to choose this tool, though it does not explicitly name alternatives or state when not to use it.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only mentions configuration and the input file, but does not disclose whether this mutates the scan config, replaces existing auth settings, or what happens on failure (e.g., wrong password). No side effects or required permissions are mentioned.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that front-loads the primary purpose and includes necessary file format details. Every word earns its place with no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a configuration/mutation operation with no output schema and no annotations. The description explains the core input and purpose but omits behavioral context such as whether the configuration is additive or replaces existing auth, or what the success/failure response looks like. It is minimally viable but lacks depth for a safe invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so baseline is 3. The description adds value beyond the schema by specifying supported traffic file formats (.har, .trec, .saz) and implying that traffic_file_id must reference an uploaded file. This enriches the meaning of the traffic_file_id parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states a specific action ('Configure') on a specific resource ('traffic-based authentication') with a concrete method ('using a previously uploaded traffic file'). It lists supported file extensions (.har, .trec, .saz), which differentiates it from sibling auth configuration tools like configure_form_auth or configure_oauth.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The phrase 'previously uploaded traffic file' clearly implies the prerequisite that the file must be uploaded before calling this tool. It also indicates the tool is for traffic-based authentication, distinguishing it from alternative auth methods, but it does not explicitly state when not to use it or name alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of disclosing behavioral implications. It merely lists actions without explaining effects, differences between stop and cancel, reversibility, or required permissions. This is insufficient for a tool that mutates scan state.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence communicates the essential purpose and actions with no filler. Every word contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and no annotations, so the description alone must convey return behavior, error conditions, and action-specific nuances. It does none of these. While the parameter list is simple, the semantic distinctions between STOP and CANCEL are left unexplained, making the description incomplete for safe autonomous invocation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides 100% coverage with descriptions for both parameters, including an enum for action. The description adds nothing beyond restating the enum values. With this coverage, a baseline of 3 is appropriate; no additional semantic value is provided.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('control') and resource ('running scan'), and enumerates the exact actions (pause, resume, stop, cancel). This clearly distinguishes it from sibling tools like submit_scan, get_scan, and delete_scan.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for controlling a running scan's lifecycle, but does not explicitly state when to use this tool versus alternatives such as delete_scan or get_scan. The context is clear but exclusions or alternatives are not mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It only says 'create', revealing nothing about side effects, permissions, idempotency, or response behavior. This is no more informative than the tool name.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single compact sentence that clearly conveys the core action without any wasted words. It is efficiently front-loaded and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a create operation with no annotations and no output schema, the description is incomplete. It fails to mention any required input constraints, expected response, or prerequisites, leaving the agent without sufficient context to invoke the tool confidently.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides full descriptions for both parameters ('name' and 'description'), so schema coverage is 100%. The description adds no additional meaning beyond the schema, resulting in the baseline score of 3.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'create' and the resource 'application', which distinguishes it from sibling tools like create_schedule or create_scan_config. However, it lacks any detail about what constitutes an application or any specifics beyond the basic action.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as create_scan_config or create_file. No prerequisites, exclusions, or context are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description discloses the main behavioral effect: creating a blackout window prevents scans. However, with no annotations, it does not provide details about side effects, whether changes are reversible, or any permissions required. Since the tool is a simple create operation and the effect is clearly stated, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that front-loads the action and purpose. It contains no filler or redundant information.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the schema's comprehensive parameter descriptions and the tool's straightforward purpose, the description provides sufficient context for an agent. It doesn't cover edge cases like overlapping windows or immediate effect, but for a create tool this is adequate. The lack of an output schema is mitigated by the simplicity of the operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage with descriptions for all five parameters. The description adds no additional parameter information, but the schema already documents name, start, stop, enabled, and all_scan_configs. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'create' with the resource 'blackout window' and clearly states the purpose: 'prevent scans during maintenance periods.' This distinguishes it from sibling tools like list_blackouts, update_blackout, and delete_blackout.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use it (during maintenance periods to prevent scans), but it does not explicitly mention alternatives or when not to use it. For example, it doesn't say to use update_blackout for modifying existing blackouts. This is clear context but no explicit exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the transparency burden. It clearly states that only the metadata entry is created, not the file content, and enumerates supported types. However, it does not mention authentication requirements, idempotency, or response behavior.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the main purpose, followed by a clear workflow pointer and a structured list of supported types. Every sentence earns its place with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a metadata-creation tool with no output schema, the description adequately covers the creation flow and how to proceed with content upload. It could mention what the response contains or error scenarios, but the core usage is well-covered.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so parameters are well-documented. The description adds extra meaning by mapping file types to their real-world file extensions (e.g., MACRO -> .rec, SWAGGER -> .json/.yaml), which goes beyond the enum labels.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Create file metadata entry.' It uses a specific verb and resource, and distinguishes itself from sibling tools by explicitly directing users to 'upload_file_content' for the actual file upload.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly provides usage context: 'After creating, use upload_file_content to upload the actual file.' This explains the workflow and points to the relevant sibling tool. Supporting file types further guides when this tool is applicable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It states the action but does not disclose side effects, permissions, idempotency, or what happens on success. For a mutation tool, this is a significant gap beyond what the name alone implies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence with no redundant wording. It states the essential purpose without any filler, making it highly concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a simple create operation with four well-documented parameters and no output schema. The description is adequate for basic understanding but lacks context about what a scan configuration is, how it relates to the application, or any prerequisites or dependencies that might affect usage.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides full descriptions for all four parameters (100% coverage), so the baseline is 3. The description adds minimal parameter meaning beyond 'for an application', which maps to the app_id parameter, but it does not add value beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Create'), the resource ('a new scan configuration'), and the scope ('for an application'). This distinguishes it from sibling tools like update_scan_config or list_scan_configs, which have different verbs and resources.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied by the verb 'Create' and the resource type, but there is no explicit guidance on when to choose this over alternatives or any prerequisites. The phrase 'for an application' gives some context, but no exclusions or alternative references are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It only says 'create', with no disclosure of side effects, validation behavior, response format, or error cases. The 'recurring' wording may also mislead for one-time (ONCE) schedules.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence with no filler. It is easy to parse and immediately conveys the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a create tool with 4 parameters and no output schema, the description is too thin. It does not mention what is returned, whether the referenced scan config must exist, or any constraints like conflicts with existing schedules.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully describes all four parameters with types, defaults, and an example for first_start. The description adds no extra parameter context, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (create) and resource (scan schedule), and is distinct from sibling schedule tools like update_schedule and delete_schedule. However, it says 'recurring scans' while the frequency enum includes ONCE, which is slightly misleading.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The usage is implied: you use this to create a new schedule. There is no explicit mention of when to prefer this over alternatives, exclusions, or prerequisites. The agent must infer from the verb and the sibling tool names.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the burden of behavioral disclosure. It clearly states the destructive cascade effect: deleting the application will also delete scan configs, scans, and vulnerabilities. This adds meaningful behavioral context beyond the simple 'Delete an application' statement, though it stops short of explicitly stating irreversibility or permission requirements.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two sentences with no wasted words. The primary action is front-loaded in the first sentence, and the second sentence efficiently adds the crucial cascading behavior. Every phrase earns its place.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the low complexity (one required parameter), no output schema, and no annotations, the description is largely complete. It explains the core deletion action and the critical side effects. A minor gap is the lack of an explicit warning about irreversibility, but the cascade disclosure covers the most important contextual need.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for the single app_id parameter, which is clearly described as the unique identifier of the application to delete. The tool description does not add additional parameter-related meaning, so the baseline of 3 applies since the schema already documents the parameter fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb+resource, 'Delete an application,' and distinguishes this tool from sibling deletion tools like delete_scan and delete_schedule by targeting the application itself. It also clarifies the cascading scope by mentioning deletion of associated scan configs, scans, and vulnerabilities.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when an application and its entire associated data need to be removed, but it does not explicitly state when to use this tool versus alternatives such as delete_scan or delete_scan_config. No exclusions or alternative tool guidance is provided, so guidance is inferred rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. 'Delete' implies destructive behavior, but the description does not explain irreversibility, required permissions, or what happens if the blackout is in use. This is a significant gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that communicates the core purpose without unnecessary words. It is appropriately sized for the simplicity of the operation.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description adds no value beyond the tool name and schema. There is no mention of return values, errors, or behavioral context. For a destructive operation with no annotations and no output schema, this is insufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% and clearly documents the blackout_id parameter. The tool description adds no additional parameter meaning, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Delete a blackout window' clearly identifies the action (delete) and the resource (blackout window), and it distinguishes itself from sibling CRUD tools like create_blackout and update_blackout. It is specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided for when to use this tool versus alternatives. The description does not mention prerequisites, side effects, or when not to use it. For a delete operation, it would be helpful to note that it permanently removes the blackout.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description only states the basic action without disclosing behavioral traits such as irreversibility, permission requirements, or side effects. It does not mention whether deletion is permanent or if there are dependencies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single clear sentence, front-loaded with the action, and contains no unnecessary words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (2 required parameters, no output schema, no annotations), the description is incomplete as it does not specify return behavior, permanence, or prerequisites. It minimally covers the core action but lacks context an agent would need for a destructive operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides full descriptions for both parameters (app_id and file_id), achieving 100% coverage. The tool description adds no additional parameter meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function with a specific verb ('Delete') and resource ('file'), and the mention of 'from an application' distinguishes it from other delete tools for schedules, blackouts, apps, scans, and scan configs. It fully explains what the tool does.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, such as when to use delete_app or delete_scan. No criteria or scenarios are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the burden. It discloses the key behavioral restriction (FAILED status only), which is valuable. However, it does not mention whether deletion is permanent, whether associated data is affected, or any permission requirements. For a destructive operation, this is a moderate gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is two short sentences with no redundant information. Every word earns its place, and the constraint is stated directly after the purpose without any filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a single-parameter tool with no output schema and a simple operation, the description covers the essentials: what it does and the one critical precondition. It is not overly complex, so no further explanation of return values or side effects is strictly needed, though a note on permanence would have made it complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers 100% of the parameters, with scan_id already having a clear description ('The unique identifier of the scan to delete'). The description adds no additional parameter semantics, but the baseline of 3 applies since the schema does the work.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb-resource pair ('Delete a scan') and adds a crucial constraint ('Only scans in FAILED status can be deleted'), clearly distinguishing this from sibling delete tools like delete_schedule or delete_scan_config. The resource and action are unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description clearly indicates when the tool is applicable: only for scans in FAILED status. This serves as an implicit exclusion (do not use for non-FAILED scans), though it does not explicitly name alternatives or say what to do instead. The context provided is sufficient for basic usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of disclosing behavioral traits, but it only restates the action. It fails to mention whether deletion is permanent, what happens to associated data, required permissions, or any side effects.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence with no redundant words. It is appropriately sized for such a simple tool and front-loads the essential action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a destructive operation with no annotations and no output schema, the description is too sparse. It does not explain the result of success/failure, whether the action is reversible, or any special conditions, making it incomplete for practical use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already provides 100% coverage for the single parameter with a clear description. The tool description adds no further parameter detail, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Delete a scan configuration' uses a specific verb and resource, clearly distinguishing it from sibling delete tools that target different entities (schedule, blackout, app, scan, file). The purpose is unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives. It does not mention any prerequisites, context, or exclusions, leaving the agent to infer usage solely from the tool name and schema.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. 'Delete a scan schedule' implies a destructive operation but does not mention side effects, such as whether associated scans are canceled, whether the deletion is reversible, or if any confirmation is required. This lack of transparency is a notable gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that conveys the tool's purpose without any redundant or extraneous information. It is appropriately sized for a simple delete operation, and every word contributes meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the tool is simple (one parameter, no output schema), the description is minimal and lacks critical contextual details such as side effects, reversibility, or relationship to schedules and scans. Given the absence of annotations and output schema, the description is incomplete for a destructive operation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully documents the only parameter (schedule_id) with a description and UUID format, so the schema coverage is 100%. The description adds no additional parameter semantics, which aligns with the baseline score of 3 when the schema already provides complete parameter information.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Delete') and the resource ('a scan schedule'), using a specific verb and noun. This unambiguously distinguishes it from sibling tools like list_schedules, create_schedule, and update_schedule.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. For example, there is no mention of prerequisites, such as whether a schedule can be deleted if it is currently active, or any note about using delete_blackout for blackout schedules instead. The description offers no contextual usage cues.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations, so the description carries the full burden. It discloses the output encoding (base64) but omits any behavioral details such as whether the operation is read-only, potential size limits, or what happens if the file does not exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, compact sentence that states the verb, resource, and output format without any redundant words. It is front-loaded and highly concise.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple two-parameter tool with no output schema, the description provides the key return format (base64 string) but lacks clarification on the full response structure or any constraints. It is minimally acceptable but leaves some gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% for both parameters, adequately defining app_id and file_id. The description adds no extra parameter meaning, but the schema already provides sufficient clarity, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Download') and the resource ('file content') as well as the output format ('base64-encoded string'). It is specific and understandable, but does not explicitly differentiate from sibling tool get_file, which might also retrieve file-related information.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives like get_file or list_files. The description does not mention prerequisites, exclusions, or typical use cases.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. It does not disclose whether report generation is asynchronous, what permissions are required, or any side effects. The existence of get_report_status suggests async behavior, but the description omits this entirely.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words. It effectively states the core purpose, though it lacks depth. The brevity is appropriate for conciseness, but not for completeness.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with five parameters, two enums, and no output schema or annotations, the description is notably incomplete. It does not explain conditional parameter usage (e.g., scan_id for scan-type reports vs app_id for others), return behavior, or the likely asynchronous nature of report generation.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage of all five parameters with descriptions, so the baseline is 3. The description adds no additional meaning about parameters; it even fails to mention the 'compliance' report type that exists in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's action ('Generate') and resource ('a new vulnerability report'), with scope ('for an application or scan'). It distinguishes from siblings like list_reports and get_report_status by emphasizing creation of a new report.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives. The description does not mention list_reports or get_report_status, nor does it provide any exclusions or context about choosing report types beyond a passing mention of application or scan.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

There are no annotations to rely on, so the description must carry the behavioral transparency burden. It only says 'Get detailed information' without disclosing what information is returned, whether the operation is read-only, error behavior for non-existent app IDs, or permission requirements. This is minimal disclosure for a read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is direct and free of extraneous words. It is appropriately sized for a simple getter tool and front-loads the core purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and no output schema, and the description gives a basic idea of its function. However, 'detailed information' is vague and does not specify what information is included, such as configuration, status, or tags. It is minimally complete but lacks useful contextual detail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% coverage for its single parameter, app_id, with a clear description. The tool description adds no additional parameter semantics, but the schema already provides sufficient meaning. This aligns with the baseline of 3 for high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function: retrieving detailed information about a specific application. The verb 'get' and resource 'application' are precise, and the word 'specific' implicitly distinguishes it from list_apps, which likely lists multiple applications. However, it does not explicitly name the alternative or the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. It does not mention that app_id can be obtained from list_apps, nor does it state any prerequisites or exclusions. The description simply restates the tool's action without contextual direction.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. However, it only says 'Get detailed information', which is essentially a restatement of the purpose. It does not disclose return format, error handling, permissions, or any side effects. This is minimal transparency for a read operation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no unnecessary words. It states the action and the target concisely, making it easy for an agent to parse quickly.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple single-parameter get tool, the description is minimally adequate, but 'detailed information' is vague and does not indicate what fields or data the response will contain. No output schema exists, so the description should provide more context about the return value, but it does not. The tool is likely straightforward, but the description leaves room for ambiguity.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, with blackout_id described as 'The unique identifier of the blackout window'. The tool description adds no additional meaning about the parameter beyond what the schema already provides, so the baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's function with a specific verb ('Get') and resource ('detailed information about a specific blackout window'). It distinguishes itself from sibling tools like list_blackouts (which lists blackouts) and create/update/delete by focusing on a single, specific window.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving a single blackout window by ID, but it does not explicitly state when to use this tool over alternatives like list_blackouts, nor does it mention any prerequisites or exclusions. The context is clear but the guidance is implied rather than stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only mentions 'detailed information' without revealing permissions, error behavior, return format, or any side effects. The read-only nature is implied but not explicitly disclosed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, clear sentence that front-loads the verb and object. It contains no filler or redundant information and is appropriately sized for a simple tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get-by-ID tool with no output schema, the description is functional but minimal. It does not specify what 'detailed information' includes or mention any caveats, though the tool's simplicity and complete parameter schema mitigate the absence.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema fully documents the engine_id parameter with a clear description (100% schema coverage). The description adds no additional meaning beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose with a specific verb 'Get' and resource 'detailed information about a specific scan engine'. This distinguishes it from sibling tools like list_engines, which lists all engines, and get_engine_group, which targets a different resource.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving a single engine by ID via the word 'specific', but it does not explicitly state when to use this tool versus alternatives like list_engines. No exclusions or alternative tool references are provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full responsibility for behavioral disclosure. It states only that the tool 'gets detailed information,' but does not describe what information is included, whether it is read-only, any required permissions, error conditions, or response format. This is a minimal disclosure that leaves significant ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that is front-loaded with the verb and object. There is no redundant wording or extraneous details. It is appropriately sized for a simple getter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (one parameter, no output schema, no annotations), the description is minimally adequate. However, it does not explain what 'detailed information' includes, nor does it clarify return format or behavior. For a tool that purportedly returns detailed information, some elaboration on the response would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema description covers 100% of the single parameter, engine_group_id, providing its type and meaning. The description adds no extra semantic information. Since schema coverage is high, a baseline of 3 is appropriate, and there is no additional value from the tool description.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'Get detailed information about a specific engine group.' The verb 'get' and resource 'engine group' are specific, and the word 'specific' distinguishes it from list operations like list_engine_groups. However, it does not explicitly mention alternatives or contrast with sibling tools, so it falls short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives such as list_engine_groups or get_engine. No prerequisites, context, or exclusions are provided. The description offers no usage direction beyond the basic action.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden. However, it only states the action and resource, without disclosing any behavioral traits such as authentication requirements, error behavior (e.g., 404 if file not found), return format, or whether the operation is read-only. The verb 'get' implies read-only, but this is not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence that immediately conveys the core purpose. No filler or redundant information, and it is front-loaded with the action and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simplicity of a get-by-ID metadata operation and the complete schema, the description is adequate but minimal. However, without an output schema or annotations, it does not clarify what specific metadata will be returned, error handling, or permissions, leaving some gaps for an agent relying solely on this description.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both app_id and file_id fully described as unique identifiers. The tool description adds no additional parameter semantics beyond what the schema already documents, so a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get file metadata by ID' uses a specific verb ('Get'), a clear resource ('file metadata'), and a scope ('by ID'). This clearly distinguishes it from siblings like download_file (which fetches content) and list_files (which lists multiple files).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this tool is for fetching a single file's metadata when an ID is available, but it does not explicitly state when to use it versus alternatives. No exclusions or alternative tool mentions are provided, so the context is clear but lacks explicit guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry behavioral disclosure; it only states the operation, omitting return shape, failure behavior for unknown reports, whether status is pollable, or authentication/permissions. Since it's a read/get operation, there is some safe inference from the name, but no concrete details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single front-loaded sentence with no filler; every word contributes to the core purpose. Appropriate size for a simple one-parameter tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the simple one-parameter schema and no output schema, the description covers the basic operation but lacks any return value details or usage caveats. It is minimally viable but not rich; no annotations or output schema place more burden on the description, so it falls short of complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with a single report_id parameter described as 'The unique identifier of the report'. The description adds only the context that the report is 'generated', which doesn't materially enrich parameter semantics beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Get') and identifies the resource ('status and details of a generated report'), clearly distinguishing it from sibling list_reports and generate_report tools. However, it doesn't further distinguish from similar single-report retrieval tools or qualify scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool vs alternatives; it doesn't mention that it should be used only after generate_report, nor exclude alternative retrieval paths. The intended usage is only implied by the tool name.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It states 'Get detailed information' which implies a read-only operation, but does not explicitly confirm no side effects, required permissions, or possible errors. For a simple getter, the description is minimal but acceptable; however, it adds little beyond what the tool name implies.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence with no redundancy or filler. It efficiently communicates the core function without wasting tokens.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is low complexity (one parameter, no nested objects) and the schema is thorough for inputs. However, there is no output schema, and the description does not specify what 'detailed information' includes or how it differs from related scan tools like get_scan_execution_details. The description is adequate for a simple getter but leaves some ambiguity about return content.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema covers 100% of the single parameter (scan_id) with a clear description. The tool description adds no additional meaning beyond the schema, but the schema already provides sufficient semantic information. Baseline 3 is appropriate given high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the verb 'Get' and the resource 'scan' with the scope 'specific' and 'detailed information'. It distinguishes from list_scans (which lists multiple scans) but does not explicitly differentiate from sibling tools like get_scan_execution_details. Clear but lacking explicit sibling differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description does not mention prerequisites (e.g., having a scan_id), nor does it suggest when to choose get_scan over get_scan_execution_details or list_scans. There are no usage context or exclusion notes.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It indicates a read-only operation ('Get'), but provides no additional behavioral context such as response format, possible errors, or effects. It does not contradict any annotations because none exist.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that directly states the tool's purpose. Every word adds meaning, with no filler or redundancy. It is concise and well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple with one parameter and no output schema, so a brief description is reasonable. However, without an output schema, the description should ideally indicate what 'detailed information' includes (e.g., configuration settings, scan engine, targets). The current description is minimally adequate but leaves the return content vague.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%: the single parameter scan_config_id is described as 'The unique identifier of the scan configuration.' The description adds no new meaning beyond confirming it targets a specific configuration. With full schema coverage, a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('Get') and a specific resource ('detailed information about a specific scan configuration'), clearly indicating it fetches one configuration. This distinguishes it from sibling tools like list_scan_configs (which lists all configs) and get_scan_config_options (which retrieves options).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description offers no guidance on when to use this tool versus alternatives. It does not mention that an ID is required or that list_scan_configs should be used to discover IDs. No exclusions or alternative tools are referenced.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry behavioral disclosure. It only states what is retrieved, without noting side effects, required permissions, or return structure. 'Get' implies read-only but is not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

One concise sentence with the verb and resource front-loaded. No wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple read tool with one parameter, the description is adequate but does not compensate for the missing output schema or annotations. It hints at the return ('full options') but does not specify the structure or edge cases.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Input schema has 100% coverage with a clear description for scan_config_id. The tool description does not add any parameter-level semantics beyond indicating it returns options, but schema already handles the single parameter.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific action ('Get') and resource ('full scan configuration options'), and adds a distinctive scope ('including authentication settings'). However, it does not explicitly differentiate from get_scan_config, though the name implies a broader options list.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance on when to use this tool versus get_scan_config or the auth configuration tools (configure_form_auth, configure_oauth, etc.). It does not mention prerequisites or context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. The verb 'Get' implies a read-only operation, but it does not explicitly state whether the operation has side effects, how pagination works beyond the schema, or what the response format is. It is minimally transparent but not misleading.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the core action and object. It contains no unnecessary words or repetition, making it highly efficient for its minimal purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a simple log retrieval with a well-documented schema, but the absence of an output schema means the description should have explained the expected return structure or event format. It does not, leaving a gap in contextual completeness for an agent unfamiliar with the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema provides 100% coverage of all three parameters, including descriptions for defaults and constraints. The description adds no additional parameter semantics beyond what the schema already offers, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Get' with a clear resource ('engine event logs') and scope ('for a scan'), which precisely distinguishes it from sibling tools like get_scan or get_scan_execution_details. It unambiguously states the tool's primary function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as get_scan_execution_details or get_scan. While the purpose implies its use cases, it lacks explicit exclusions or context that would help an agent select it correctly.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. 'Get' implies a read operation, and 'real-time' suggests current data, but it does not clarify whether the call is non-mutating, what specific metrics are returned, or if there are any rate limits or prerequisites. The 'running or completed' clause adds some context, but transparency remains partial.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence with no wasted words. It front-loads the action and resource, making it immediately clear what the tool does.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is simple (1 param, no output schema), but the description leaves 'execution metrics' undefined. It would be more complete with a brief list of example metrics (e.g., progress, duration, status). Given the low complexity, the description is adequate but not thorough.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% (scan_id is defined), so the baseline is 3. The description doesn't add extra meaning beyond the schema; it just confirms the tool operates on a scan. No further elaboration on the parameter is needed given the high schema coverage.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the verb ('Get') and resource ('real-time execution metrics for a scan'), which distinguishes it from sibling tools like 'get_scan' (which likely returns general scan details) and 'control_scan' (which performs actions). It also specifies scope: running or completed scans.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when real-time execution metrics are needed, but it does not explicitly state when to use this tool versus alternatives such as 'get_scan' or 'get_scan_engine_events'. No exclusions or conditional guidance is provided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full responsibility for behavioral disclosure. It indicates a read operation via 'Get', but does not explicitly state it is read-only, mention authentication needs, or describe failure behavior or response format. The minimal description leaves significant behavioral context unstated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, focused sentence with no wasted words. It is concise and directly states the tool's purpose.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get operation, the description is adequate but lacks details about the return value. Since there is no output schema, the description could clarify what 'detailed information' includes, but it does not. The tool is straightforward, but completeness is slightly compromised by the vague term 'detailed information'.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 100% coverage for the single parameter schedule_id, and the description adds no additional meaning beyond the schema. Baseline 3 is appropriate because the schema already documents the parameter adequately.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb 'Get' and resource 'specific schedule', clearly distinguishing it from sibling list_schedules which lists schedules. It unambiguously identifies the action and target.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage for retrieving details of a single schedule, but it does not explicitly state when to use it instead of list_schedules or mention any exclusions or prerequisites. Usage context is only implied, not clearly articulated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description makes the read-only nature clear by using 'get', but it does not disclose return format, whether the vulnerability object contains all fields, or any error/not-found behavior. Since no annotations are provided, the description partially carries the transparency burden but leaves gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no wasted words. It immediately states the action and target resource and is appropriately sized for a simple getter.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple get-by-ID tool with one well-documented parameter, the description is mostly complete, but 'detailed information' is vague and there is no output schema. It could state that the full vulnerability object is returned or mention any notable fields.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The parameter vulnerability_id is fully described in the schema (UUID, unique identifier). The description adds little beyond 'specific vulnerability', which corresponds directly to the parameter. Schema coverage is 100%, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Get detailed information about a specific vulnerability' uses a specific verb ('get') and resource ('vulnerability'), and the phrase 'specific vulnerability' distinguishes it from list_vulnerabilities and get_vulnerability_discoveries. It clearly communicates the tool's core function.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when a user needs details for a single vulnerability by ID, but it does not explicitly mention when to use this over list_vulnerabilities or get_vulnerability_discoveries. No alternatives or exclusion criteria are stated.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states 'Get', which implies read-only behavior but does not explicitly confirm it, nor does it mention pagination, response format, error handling, or any side effects. This is insufficient for a tool with no annotation support.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that is efficient and easy to parse. However, it is extremely terse, lacking any additional context that might be expected for a tool with no annotations or output schema, so it does not fully earn the top score for structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

With no output schema and no annotations, the description is expected to provide context about the return format and behavior. It fails to explain what 'discovery history' contains, how pagination works, or what the response structure is, leaving the agent under-informed for a tool that might return varied historical data.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage with descriptions for all three parameters, so the baseline score of 3 applies. The tool description itself adds no parameter-level meaning, but since the schema already documents size, index, and vulnerability_id, the description does not need to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Get') and the specific resource ('discovery history for a vulnerability'), distinguishing it from sibling tools such as get_vulnerability (which retrieves vulnerability details) and list_vulnerabilities (which lists vulnerabilities). The verb+object structure is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, nor does it mention any prerequisites, exclusions, or context. It is a bare statement that leaves the agent to infer usage from the name alone, offering no differentiation from related tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. 'List' implies a read-only operation, and 'optional pagination and sorting' gives some behavioral context, but it doesn't disclose limitations, permissions, or return format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, well-front-loaded sentence with no wasted words. It efficiently conveys the core purpose and optional features.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with well-documented parameters, the description is largely complete. It covers the core functionality and mentions pagination/sorting, though it doesn't describe the return shape or clarify 'all applications' scope.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the baseline is 3. The description's mention of 'optional pagination and sorting' aligns with the size, sort, and index parameters but adds no meaning beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action 'List' and the resource 'applications', making it distinct from sibling tools like get_app. Mention of 'optional pagination and sorting' adds a specific scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives such as get_app for a single application. The description neither gives context nor exclusions, so the agent is left without guidance.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral transparency. It only states the action and pagination option, but does not disclose that this is a read-only operation, what the return format is, whether all blackout windows are returned, or any default ordering/limitations. This is a significant gap for an unannotated tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence of seven words ('List blackout windows with optional pagination'), front-loaded with the verb and resource. There is no redundancy or filler; every word contributes to the meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is relatively simple with only two optional parameters and no output schema, so the description does not need much. However, it omits any statement about what the return value looks like (e.g., a list, paginated response), whether all blackouts are returned by default, or any filtering/ordering behavior. While adequate for a basic list, it leaves some uncertainty for an agent invoking the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both 'size' and 'index' fully documented including defaults, bounds, and descriptions. The description's phrase 'optional pagination' adds no extra meaning beyond what the schema already provides, so the baseline of 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses the specific verb 'List' and resource 'blackout windows', clearly identifying the tool's function. This distinguishes it from sibling tools like get_blackout, create_blackout, and delete_blackout. The mention of 'optional pagination' adds relevant detail without obscuring the core purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool versus alternatives. The description does not mention using get_blackout for individual blackout details or create_blackout for creating windows. The only hint is 'optional pagination', which is more of a parameter feature than usage context, leaving the agent without explicit selection criteria.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description must carry the burden of behavioral disclosure. It only says 'List engine groups with optional pagination' but does not explain behavior such as default page size, max page size, response format, sorting, or whether it returns a full list or only metadata. The read-only nature is implied but not stated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that conveys the core action and resource without unnecessary repetition. It is concise and to the point, with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with two optional parameters and no output schema, the description is minimally adequate. It identifies the resource and mentions pagination, but it does not describe the return value or any response structure, which would be helpful given the absence of an output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with both size and index parameters fully documented in the schema. The description adds minimal meaning by saying 'optional pagination', which merely reinforces that pagination is optional without providing additional semantic detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and the resource ('engine groups'), making the tool's purpose immediately understandable. However, it does not explicitly differentiate from sibling tools like list_engines or get_engine_group, relying on the name to imply the distinction.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It neither mentions scenarios where this tool is appropriate nor points to sibling tools for different use cases (e.g., getting a single engine group via get_engine_group).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the list operation and optional pagination, but doesn't explicitly confirm read-only behavior, return format, or any side effects. This is minimal behavioral transparency.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is one concise sentence with no redundant words. The verb and resource are front-loaded, and every word contributes to the meaning.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

While the tool is simple and parameters are well-covered by the schema, the description omits the return format or list of engine fields, and doesn't differentiate from similar list tools. Given no output schema and no annotations, the description leaves some gaps in fully understanding the tool's behavior and output.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema already fully describes both parameters (size and index) with defaults and bounds. The description adds only 'optional pagination', which provides no additional semantic detail beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the action ('List') and the resource ('registered scan engines'), and mentions pagination as an optional feature. This distinguishes it from sibling tools like get_engine (single engine) and list_engine_groups (groups).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as get_engine or list_engine_groups. There is no mention of exclusions, context, or comparison with sibling list tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden for behavioral disclosure. It only states 'List all files,' which implies a non-destructive read but does not mention pagination (size/index), ordering, return format, or required permissions. It adds context about file types (macros, traffic files, selenium scripts) but remains thin on operational details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence (about 13 words) that efficiently conveys the action, scope, and examples. Every word adds value, and there is no redundancy or filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with 3 parameters and no output schema, the description is mostly complete. It explains what resource is listed and gives examples of file types, and the schema thoroughly documents pagination. However, it does not explicitly state that the operation is read-only or what the response contains (metadata vs. content), which would enhance completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3. The description adds value beyond the schema by explaining what kinds of files are meant ('macros, traffic files, selenium scripts, etc.'), giving semantic context to the resource. It does not duplicate parameter details, but the file-type examples provide helpful disambiguation.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'List all files for an application' with a specific verb (List), resource (files), and scope (for an application). It also distinguishes from siblings like get_file and create_file by specifying the listing action and the application context.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies when to use the tool (when you need to list a specific application's files), but it does not explicitly state exclusions or alternatives such as 'use get_file to retrieve a specific file' or 'use list_apps to view applications.' Clear context is present, but no when-not-to-use guidance is given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It states 'List' which implies a read operation, but it does not disclose important behaviors such as whether results are sorted, whether the default page size is 50, or whether any filtering is implied. The optional pagination is mentioned but not elaborated.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no extraneous words. Every word contributes to the core meaning, making it highly efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool, the description lacks critical context: no output schema, no mention of what fields are returned, and no indication of prerequisites (e.g., whether reports must be generated first). Given the sibling tools, more context would help an agent know when to invoke this tool and what to expect.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema fully documents the size and index parameters. The description adds minimal value beyond hinting at 'optional pagination' but does not introduce new meaning or constraints.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists generated reports, which is a specific verb+resource combination. It distinguishes itself from siblings like generate_report and get_report_status, though it could be clearer about what constitutes a 'generated report'.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use this tool vs alternatives. There are many list_* siblings, and the description does not explain scenarios where list_reports is preferred (e.g., enumerating available reports vs checking a specific status).

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It states only 'List scan configurations with optional pagination' but does not disclose default behavior (e.g., default page size, default sort order, whether all configs are returned or only those accessible to the user). The term 'list' implies read-only, but this is not explicit, and no details about response format, errors, or rate limits are provided.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that communicates the core function and a key option (pagination) without any unnecessary words. It is appropriately concise for a simple list operation and follows a clear subject-verb-object structure.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool's simplicity (3 optional parameters, no output schema, no annotations), the description is minimally adequate but lacks important context. It does not mention the sort parameter, which is part of the schema, nor does it clarify default pagination behavior or differentiate from similar listing tools. For a list operation, more detail about return values (even without an output schema) would improve completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% parameter description coverage, with each parameter (size, sort, index) having its own description. The tool description adds no additional meaning beyond the schema; it merely mentions 'optional pagination' which is already implied by the size and index parameters. Thus, a baseline score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb+resource combination: 'List scan configurations' clearly indicates this tool retrieves scan configuration records. It distinguishes from sibling tools like list_scans (which lists scans, not scan configs) and get_scan_config (which retrieves a single config). The phrase 'with optional pagination' further clarifies scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no explicit guidance on when to use this tool versus alternatives. While the name implies a listing operation, it does not mention that get_scan_config is for single items or that create/update/delete are for mutations. No exclusions or alternative recommendations are given.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden. It mentions optional pagination, sorting, and filtering, which are useful behavioral details. However, it does not explicitly confirm that the operation is read-only, describe the response format, or disclose any limitations or side effects. For a list operation, this is adequate but not rich.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence: 'List scans with optional pagination, sorting, and filtering'. Every word adds value, with no redundancy or filler. It is concise and structurally effective.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool is a simple list operation with three optional parameters and no output schema. The description covers the core functionality and parameter options, but it does not mention what the response looks like, how to interpret results, or specific domain context. Given the simplicity, this is acceptable but leaves some room for improvement.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all three parameters (size, sort, index). The description references these concepts (pagination, sorting, filtering) but adds no additional meaning or syntax details beyond what the schema already provides. Per the baseline for high schema coverage, a score of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (List) and the resource (scans). It distinguishes the tool's purpose from siblings like get_scan or submit_scan, though it does not explicitly exclude other list tools. The mention of pagination, sorting, and filtering adds scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is given on when to use this tool versus alternatives such as get_scan (for a single scan) or other list tools (list_vulnerabilities, list_engines). The description only says 'List scans', which implies the use case but does not provide explicit context or exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It only says 'List' and 'optional pagination', which adds little beyond the name and schema. It does not explain what the response looks like, whether results are ordered, or any side effects. This is a significant gap for a tool with zero annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence that conveys the core purpose and optional pagination without waste. It is appropriately concise for the simplicity of the tool.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description covers the essential action and pagination, and the schema handles parameter details. However, it does not describe the return structure, or clarify if any default filtering applies. For a list tool with no output schema and no annotations, this is adequate but leaves gaps.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides 100% coverage with descriptions for both 'size' and 'index', including defaults and constraints. The description's mention of 'pagination' adds minimal context since the schema already makes this clear. Baseline 3 applies.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('List') and resource ('scan schedules'), distinguishing it from sibling tools like get_schedule, create_schedule, update_schedule, and delete_schedule. It also mentions optional pagination, adding scope.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies this is the list operation for schedules, and the pagination mention suggests when to use size/index. However, it does not explicitly state when to prefer this over get_schedule or mention any exclusions or alternative tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden, but it offers little beyond 'List vulnerabilities' and an unsupported 'filtering' claim. It does not explicitly confirm that the operation is read-only, describe the return format, or note any behavioral constraints such as pagination defaults already in the schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no filler. However, it loses a point because the inclusion of 'filtering' is inaccurate and not supported by the schema, making the conciseness slightly misleading.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple list tool with fully described optional parameters, the description is nearly adequate, but the unsupported 'filtering' claim and lack of any mention of the response structure (no output schema) leave gaps. An agent could attempt to pass a filter parameter and fail.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so the schema already documents all three parameters. The description groups size/index as pagination and sort as sorting, adding minimal high-level context, but the 'filtering' mention is misleading because no filter parameter exists.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool lists vulnerabilities, using a specific verb and resource, and mentions optional pagination, sorting, and filtering. It is distinct from siblings like get_vulnerability or update_vulnerability, but the claim of 'filtering' is not supported by any parameter in the schema, which slightly undermines accuracy.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to use this tool versus alternatives. It does not mention that get_vulnerability retrieves a single vulnerability or that list_vulnerability_comments handles comments, leaving the agent without context for selection among sibling tools.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden. It only states the operation without disclosing the read-only nature, return format, pagination, or any side effects. This is insufficient for a tool with no output schema.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

A single, front-loaded sentence with no filler. Every word adds meaning; there is no unnecessary detail.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one param and no output schema, the description is functional but incomplete—it does not explain what a comment includes, whether results are paginated, or any ordering. Given missing annotations, more context would be beneficial.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully documents vulnerability_id (100% coverage), so the description adds little parameter-specific value. It reinforces that comments are associated with a vulnerability but provides no additional format or behavior details.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description uses a specific verb ('List'), identifies the resource ('comments on a vulnerability'), and clarifies scope ('all'). This clearly distinguishes it from sibling tools like add_vulnerability_comment and get_vulnerability.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies the tool's purpose but provides no explicit guidance on when to use it over alternatives. It does not mention that add_vulnerability_comment is for adding comments, nor does it state any exclusions or conditions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does state that the tool adds or removes tags, which is a clear mutation operation, but it does not mention idempotency, permissions, effects on existing tags, or what happens when adding/removing an already-associated tag. It is minimally transparent but not richly so.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that immediately conveys the core function. It is front-loaded and contains no unnecessary words or repetition, earning it a perfect score for efficiency.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has three fully documented parameters and no output schema, making it a simple mutation operation. The description is sufficient for understanding the action, but it lacks any mention of the expected response or side effects, which could leave an agent unsure about what to expect after invocation. It is adequate but not comprehensive.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100% with each parameter (action, app_id, tag_id) clearly documented. The description itself adds no additional parameter semantics beyond what the schema already provides, so it meets the baseline of 3 but does not exceed it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Add or remove tags') and the resource ('an application'), making the tool's purpose immediately understandable. It distinguishes itself from sibling tools because no other tool in the list appears to manage tags, though it does not explicitly call out this differentiation.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives, such as update_app or other application-related tools. It gives no context on scenarios where tag management is appropriate or where it should be avoided.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the behavioral disclosure burden. It does explain the query language (operators: =, !=, CONTAINS, IN, AND, OR) with examples, which is essential behavioral context. However, it does not disclose pagination behavior, error handling, authentication requirements, or what fields are searchable beyond the examples, leaving gaps.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is front-loaded with the core purpose in the first sentence. The three example lines efficiently illustrate typical usage, and the operator list is concise. No filler sentences; each element serves a purpose. It is slightly longer than necessary but well-structured.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a tool with a complex DSL, no output schema, and four parameters, the description provides the necessary query syntax, operators, and use cases. It does not describe the return value format or pagination details, but those are partially covered by the schema's size/index descriptions. The description is sufficient for an agent to understand how to construct valid searches.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all 4 parameters, so the baseline is 3. The description adds value by showing exact DSL query strings for the 'query' parameter (e.g., "vulnerability.severity='HIGH'") and pairing the 'type' parameter with resource examples. This enriches semantic understanding beyond the schema's plain descriptions.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with 'Universal search across InsightAppSec resources using DSL query syntax,' which clearly identifies a specific action (search), resource domain (InsightAppSec resources), and distinguishing syntax (DSL). It also includes concrete examples for vulnerabilities, scans, and apps, making the purpose unmistakable and distinct from sibling list/get tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description does not explicitly contrast with sibling list_* tools or state when to use search versus dedicated list endpoints, but the 'Universal search' framing and examples (e.g., filtering vulnerabilities by severity) strongly imply it is intended for flexible cross-resource querying. However, no explicit exclusions or alternatives are given, so it falls short of a 5.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, and the description only says 'Submit a new scan.' It does not disclose whether submission is asynchronous, whether specific permissions are needed, or what the response contains, leaving the agent without important behavioral context.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single concise sentence, front-loaded with the action and resource, with no unnecessary filler or repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple one-parameter tool with no output schema and no annotations, the description is minimally adequate for selecting the tool, but it lacks details about return values, execution flow, or side effects.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The schema fully documents the single parameter scan_config_id with its UUID format and description. The description's phrase 'based on a scan configuration' adds no new meaning beyond the schema, so it meets the baseline but does not exceed it.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly identifies the action ('Submit'), the resource ('a new scan'), and the basis ('a scan configuration'), which distinguishes it from sibling tools like control_scan or list_scans.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when launching a scan from an existing configuration, but it offers no explicit guidance on when to prefer it over alternatives or any prerequisites.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only restates that an update occurs and does not explain whether updates are partial or full, how nonexistent app IDs are handled, required permissions, or what response is returned. This is a notable transparency gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with zero wasted words. It immediately communicates the action and target resource, making it efficient and easy to parse.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has a simple schema with a required app_id and optional fields, and the description covers the basic action. However, with no output schema and no annotations, details about return values, error behavior, and side effects are absent. It is minimally viable but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, with each parameter (app_id, name, description) already documented in the input schema. The tool description adds no additional meaning beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Update an existing application' uses a specific verb and resource, clearly identifying the tool's purpose. The word 'existing' distinguishes it from create_app and delete_app, and the resource name differentiates it from update_vulnerability, update_schedule, and other update siblings.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description implies usage when an existing application needs to be modified, but it does not explicitly state when to use this tool over alternatives or mention exclusions. There is no guidance on preferring this over create_app or delete_app, leaving context implied rather than explicit.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the full burden of behavioral disclosure. It only states the action of updating without mentioning idempotency, partial vs full replacement, required fields, or return behavior. This is a significant gap for a mutation tool.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, direct sentence with no unnecessary words. It is front-loaded and perfectly concise, serving its purpose efficiently.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has 5 parameters and no annotations or output schema, yet the description only provides the basic action. It omits essential details about update semantics, response format, and side effects, making it inadequate for fully understanding the tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema provides descriptions for all 5 parameters, so the baseline is 3. The description adds no additional parameter context beyond what the schema already covers, but the schema itself is sufficient.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action ('Update') and the resource ('an existing blackout window'), and it distinguishes from sibling tools like create_blackout and delete_blackout by explicitly targeting an existing entity. However, it does not specify which aspects can be updated, which would enhance clarity.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives such as create_blackout or delete_blackout. It implies that the blackout must already exist, but it lacks explicit context or exclusions, leaving the agent to infer usage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure, but it only says 'update.' It does not explain whether the update is partial or full, how missing configs are handled, or any side effects. For a mutation tool, this is a significant gap.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, front-loaded sentence with no redundancy or wasted words. It directly states the core function.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The tool has no output schema and minimal annotation support. The description does not cover important context such as update semantics (merge vs replace), required permissions, error behavior, or relation to get_scan_config / create_scan_config. This leaves significant gaps for an agent trying to invoke it correctly.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the schema fully documents each parameter (scan_config_id, name, description). The description adds no extra meaning beyond the purpose, but the schema already provides clear semantics, so baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the action (update) and the resource (scan configuration), distinguishing it from other update tools by specifying the target. However, it is fairly generic and does not mention what aspects can be updated, though the schema covers that.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

There is no guidance on when to use this tool versus alternatives like create_scan_config or delete_scan_config. The description does not mention any prerequisites or context for when an update is appropriate.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only says 'update' without specifying whether this is a partial or full update, what side effects occur (e.g., affecting running scans), or error behavior. This is insufficient for a mutation tool, as an agent cannot infer the exact impact.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence, front-loaded with the key action, and contains zero filler words. It is appropriately sized for the tool's simplicity and does not waste the agent's attention.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

The description is minimal and relies entirely on the schema for context. It does not clarify update semantics (partial vs. full), what happens if the schedule_id does not exist, or the result of a successful update. Given there are no annotations and no output schema, this is incomplete for a mutation tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The input schema has 100% description coverage for all four parameters, each with clear descriptions (e.g., 'Enable or disable the schedule', 'New frequency'). The description text adds no additional parameter semantics beyond the schema, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description 'Update an existing scan schedule' clearly identifies the action (update), the resource (scan schedule), and the scope (existing), which distinguishes it from sibling tools like create_schedule, delete_schedule, and list_schedules. The verb and resource are specific and unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.