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

No annotations are provided, so the description is the sole source. It mentions 'batch-create cognition nodes' which implies state mutation, but does not disclose destructive potential, permission levels, or side effects. Some behavioral context is added but incomplete.

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?

Single sentence front-loads the action but is relatively long (19 words). It conveys the core purpose without wasted words, but could be split for clarity. Acceptable but not optimal.

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 7 parameters, no output schema, and no annotations, the description fails to cover necessary details like return format, error behavior, or how 'cognition nodes' are created. Many sibling tools relate to cognition, but context is not provided for this specific 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 0%, and the description adds no information about any of the 7 parameters. The agent must infer meaning from names alone, which is insufficient. The description could have explained key parameters like 'deepScan', 'excludePatterns', or 'generateInitialRules'.

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 (scan), resource (project directory), and multiple outcomes (extract file stats, detect coding conventions, batch-create cognition nodes). It distinguishes itself from siblings like 'analyze_workspace' by specifying governance initialization, though does not explicitly differentiate.

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 explicit guidance on when to use vs alternatives. The description implies use for governance initialization but lacks when-not or prerequisite information. Without sibling comparisons, the agent cannot easily decide.

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 provided; the description only states the primary action without disclosing behavioral traits such as read-only nature, side effects, authorization requirements, 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 concise sentence, but it is too brief for a tool with 4 parameters and no schema descriptions. Every sentence should earn its place, but here it is under-specified.

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 (4 parameters, no output schema, no annotations), the description is incomplete. It does not cover return values, error behavior, or prerequisites, leaving significant gaps for an AI 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 0%, and the tool description does not elaborate on any parameter meaning. For a 4-parameter tool with a required baseCommit, the description adds no value beyond parameter names.

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 'analyze', the resource 'git workspace diff', and the purpose 'for rule violations'. It distinguishes from siblings like capture_diff (captures diff) and query_rules (queries rules) by specifying the analysis goal.

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 alternatives like capture_diff, query_rules, or analyze_project. The description lacks explicit context for appropriate usage 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?

No annotations are provided, and the description does not disclose any behavioral traits such as side effects, authorization requirements, or data persistence. It only states the basic action.

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, which is too brief given the tool has 5 parameters and no output schema. While concise, it lacks necessary detail, making it under-specified rather than efficiently informative.

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 does not cover return values, behavior on error, or any contextual details for a tool with 5 parameters and no output schema. It leaves significant gaps in understanding the tool's full behavior.

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?

With 0% schema description coverage and no parameter descriptions in the tool description, the agent receives no additional context beyond the property names in the schema. The description does not explain what 'filePath', 'originalContent', 'modifiedContent', 'language', or 'projectId' represent.

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 'Capture and analyze' and the resource 'code diff' with a specific purpose 'for rule violations'. It distinguishes from sibling tools like 'query_rules' which are about querying existing rules, not analyzing diffs.

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, no prerequisites, and no when-not-to-use conditions. It simply describes what it does.

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 only states the action. It does not disclose side effects, required permissions, or what happens upon each decision. For a mutation tool, this omission is significant.

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 very concise (one sentence, 7 words). It front-loads the key actions but omits necessary detail; however, it avoids jargon or redundancy. It earns its place but could expand slightly without losing 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?

Given the tool's simplicity (2 params, no output schema, no annotations), the description is incomplete. It lacks context on when a proposal is 'pending', success/failure responses, and parameter semantics. It barely meets the minimum for an agent to safely invoke it.

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 0%, so the description must compensate. It mentions the three decision values (mapping to the enum) but does not explain the 'proposalId' parameter—its meaning, format, or how to obtain it. The description adds minimal value beyond restating the enum options.

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 with precise verbs (approve, reject, override) and specifies the resource (pending injection proposal). It distinguishes itself from all sibling tools, none of which handle injection approvals.

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, when not to use it, or any prerequisites. The description simply states the action without contextual boundaries.

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 bears full responsibility for behavioral disclosure. It only states 'adjust edge weights', implying a mutation, but lacks details on side effects, permissions, idempotency, or potential consequences. Essential behavioral traits are missing.

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, making it concise. However, it is overly terse and fails to include necessary details, reducing its effectiveness. It front-loads the action but sacrifices 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?

Given 4 parameters with no schema descriptions, no output schema, and no behavioral context, the description is severely incomplete. It does not cover return values, side effects, or how the tool integrates with other cognition tools. The agent lacks sufficient information to use 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 description coverage is 0%, and the tool description provides no explanation for any of the 4 parameters. The agent cannot understand what edgeId, nodeId, comment, or outcome (beyond enum values) represent. This is a critical gap.

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 'Submit' and the resource 'feedback', indicating the action. However, it lacks differentiation from sibling tools; while no other tool directly submits feedback, the phrase 'adjust edge weights' is jargon that may not be universally understood. The purpose is specific but not fully transparent.

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 alternatives. The description does not mention prerequisites, when to avoid, or how it compares to sibling tools like cognition_query or confirm_rule. The agent must infer usage without explicit 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 full burden for behavioral disclosure. It only says 'Query', implying read-only, but does not mention side effects, authorization needs, or any other behavioral traits. This is insufficient for an agent to infer safe usage.

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, but it is under-specified. Conciseness should not sacrifice necessary detail. There is no front-loading of critical information beyond the basic 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?

Given the tool has 3 parameters (1 required), no output schema, and no annotations, the description is severely incomplete. It does not address the role of each parameter, expected output, or any contextual constraints. This tool cannot be reliably invoked from this description alone.

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 0%, yet the description adds no meaning beyond the schema. The description mentions 'from a context hash' but does not explain the purpose of other parameters (maxDepth, intentHint), nor does it clarify the format or semantics of contextHash.

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 ('Query') and the resource ('cognition graph') along with the key input ('context hash'). It distinguishes this tool from siblings like 'query_rules' or 'list_rules' by specifying the exact resource being queried.

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, nor any prerequisites or context for effective use. The description is silent on when this tool 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?

No annotations are provided, so the description must carry full burden. It only says 'Update server configuration' with no disclosure of side effects, persistence, or required permissions. This is insufficient for an agent to understand behavioral implications.

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 extremely concise but at the cost of informativeness. One sentence is too brief to convey necessary details, making it more under-specified than 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?

Given the lack of annotations, output schema, and parameter descriptions, the description is severely incomplete. It fails to provide basic context for correct invocation and expected outcomes.

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 description does not mention the two parameters ('data' and 'mode') at all, despite zero schema description coverage (0%). The agent cannot infer what values to provide for 'data' or how 'mode' affects behavior.

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 ('server configuration'), which is distinct from sibling tools that focus on queries, rules, or session management. However, it could be more specific about which server 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?

No guidance on when to use this tool versus alternatives, such as cognition_validate or cognition_query. No context about prerequisites or common 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 must disclose behavioral traits. It only states validation but omits details like side effects, permissions needed, error behavior, or return values.

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, concise and to the point. However, it could benefit from slightly more detail without losing conciseness.

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 no output schema, no annotations, and bare parameter info, the description is severely incomplete. The tool's complexity (AST validation) demands more context for 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?

Schema description coverage is 0%. The description does not explain the parameters 'nodeId' or 'targetFileContent', failing to clarify what the AST template is or how to provide code content.

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 validates code content against an AST template, using a specific verb and resource. It distinguishes itself from sibling tools like query_rules or capture_diff, which have different purposes.

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 alternatives. It does not specify prerequisites, conditions, or when not to use it, leaving the agent without context for decision-making.

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 fully carries the burden of behavioral disclosure. It does not explain what each action does (e.g., whether accepting creates a rule, rejecting deletes it, what 'edit' modifies, or what 'skip' means). The side effects are unclear.

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, which is concise but sacrifices necessary detail. It is front-loaded with the action verb, but the lack of structure or additional sentences leaves it insufficiently informative.

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 4 parameters and no output schema, the description is grossly incomplete. It does not explain when editedPattern is required, how each action affects the system, or what the tool returns. Essential context for correct usage is missing.

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 0%, so the description must compensate. However, it only mentions the actions (which correspond to the 'action' parameter), providing no explanation of ruleId, editedPattern, or editedSuggestion. Their meanings and usage are entirely absent.

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: to accept, reject, edit, or skip a suggested rule. It lists all possible actions, making the core functionality unambiguous. However, it could be improved by distinguishing it from siblings like list_rules or query_rules.

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 does not mention prerequisites, conditions for each action, or situations where another tool would be more 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?

No annotations exist, so the description must disclose behavioral traits. It mentions building a 'pending shadow Rule' but does not clarify whether the action is destructive, requires permissions, or what side effects occur. The term 'pending' is vague.

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 20 words, which is concise and front-loaded with the primary action. However, it sacrifices necessary detail for brevity.

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 8 parameters, no output schema, and a complex governance operation, the description is incomplete. It fails to explain the return value, the lifecycle of the shadow rule, or how inputs like intentConfidence and ruleType influence behavior.

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 0%, yet the description only explains the 'language, pattern, suggestion' triple but omits the other 5 parameters (intent, filePath, ruleType, projectId, intentConfidence). No parameter meaning is added beyond the schema's empty 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 states it learns a governance rule from a triple of language, pattern, suggestion, which is specific but uses jargon ('cognition closure', 'pending shadow Rule') that may obscure the core action. It does not sufficiently distinguish from sibling tools like cognition_query or confirm_rule.

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 capture_diff, query_rules, or resolve_conflict. The description lacks context for appropriate invocation 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?

No annotations provided, so the description carries full burden. It only says 'pause' but does not disclose effects, required permissions, reversibility, or behavior after N minutes. Minimal 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 one short sentence with no wasted words, but it sacrifices informativeness for brevity. Could include more detail without becoming 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?

With no annotations, no output schema, and minimal description, the tool is underspecified. Lacks information on return values, side effects, or operational context for pausing an arbitrator.

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 0%, but the description merely restates the parameter ('for N minutes') without adding meaning like consequences of different values (e.g., 1 vs 1440). Fails to compensate for missing schema 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 clearly states the action ('pause'), the resource ('automatic constraint arbitrator'), and scope ('for N minutes'). It is specific and distinguishes this tool from siblings like 'governance_rollback_arbitration'.

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, when not to, prerequisites, or alternatives. The description lacks any usage context 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?

With no annotations, the description carries the full burden of behavioral disclosure. It only states the action without describing side effects, reversibility, authorization needs, or what happens to the conflicts post-rollback.

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 efficiently conveys the core action. However, it could be expanded with critical details without losing conciseness.

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 (1 parameter, no output schema), the description is too minimal. It lacks essential context such as return values, effects on the system, and any dependencies.

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 description mentions 'ISO datetime' for the 'since' parameter but does not specify the exact format or constraints. With 0% schema description coverage, this adds minimal value beyond the parameter name.

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 'Rollback' and resource 'auto-resolved conflicts' with an ISO datetime parameter. However, it does not differentiate from sibling tools like 'resolve_conflict' or 'confirm_rule', leaving some ambiguity about the 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 'resolve_conflict'. There are no exclusions or context about prerequisites or typical scenarios.

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 provided; description only says 'with optional filters' but doesn't disclose behavioral traits like pagination, auth requirements, or potential 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?

Extremely brief at 5 words, but under-specification masks conciseness. Lacks necessary detail to be useful.

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 6 unparameterized parameters, no output schema, and no annotations, the description is grossly insufficient for an AI agent to understand tool behavior.

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 0%, and the description adds no meaning beyond parameter names. The phrase 'optional filters' is too generic to compensate for the lack of parameter explanations.

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?

Description states 'List rules with optional filters', which is a clear verb+resource. However, it does not differentiate from sibling tool 'query_rules', making it somewhat vague.

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 over alternatives like query_rules. No context 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?

Description indicates a read-only listing action but does not provide additional behavioral details beyond the obvious. Since annotations are absent, the description bears the full burden but remains somewhat minimal.

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?

Single sentence, no wasted words. Front-loaded with 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?

For a zero-parameter list tool, the description is largely complete. It covers what it does and the output content. Minor gap: could mention it only shows already loaded plugins, but that is implicit.

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?

No parameters, so baseline 4 per guidelines. Schema coverage is 100% and description adds no param info, which is acceptable.

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?

Clearly states 'List all loaded plugins with status and registered extensions', specifying the verb (list), resource (loaded plugins), and scope (all, with status and extensions). Distinguished from sibling tools like plugin_load and plugin_unload.

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 alternatives (e.g., plugin_load, plugin_unload). No when-not-to-use or prerequisites 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?

No annotations are provided, so the description must fully disclose behavioral traits. It only states the basic action without mentioning side effects like network requests (installing from NPM), file system access, validation, or whether the operation is reversible. Critical safety information is missing for a tool that loads external code.

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 conveys the core purpose without any unnecessary words or details. It is highly concise 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?

Despite having two parameters and no output schema, the description provides no information about what happens after loading (e.g., return value, errors, state changes). For a plugin loader, an agent needs to know if loading is synchronous, if it validates the plugin, or if it returns an identifier. The omission leaves significant 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 description hints that the 'source' parameter can be an NPM package name or local file path, adding some meaning beyond the schema. However, it completely ignores the 'config' parameter (a nested object), which remains unexplained. With 0% schema coverage, the description should compensate more.

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 (Load), the resource (GovernFlow plugin), and the means (from NPM package name or local file path). It is specific and distinguishes itself from siblings like plugin_unload and plugin_list, which are different operations. There is no ambiguity about 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 implies usage when you need to load a plugin, and no sibling tool provides an alternative loading mechanism, so exclusions are not needed. However, it does not explicitly state prerequisites or when not to use it, which prevents a perfect score.

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 provided. Description only implies a destructive action but does not disclose side effects, reversibility, or required permissions.

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?

Single sentence, no redundant information. Could potentially include a brief note on parameter usage, but overall 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?

With no output schema and no annotations, the description is insufficient. Does not explain what happens after unloading, confirmation, or error conditions.

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?

Only one parameter (pluginName) with 0% schema description coverage. Description adds that it can be a name or instance ID, but this is ambiguous since schema expects a string without clarifying format.

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?

Description clearly states the action (unload) and resource (plugin), with specific criteria (by name or instance ID). Distinguishes from sibling tools like plugin_load and plugin_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 vs alternatives. No mention of prerequisites or when not to unload a plugin.

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 bears full responsibility for disclosing behavior. It only states the query parameters, omitting whether the operation is read-only, what results are returned, or any side effects. The agent cannot infer safety or scope.

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 extremely concise (one sentence) but at the cost of omitting crucial information. While there is no redundancy, the brevity leads to under-specification, making it less helpful than a longer, more detailed description.

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 complexity (7 parameters, no output schema, no schema descriptions), the description is severely incomplete. It does not cover return values, error conditions, or the behavior of optional parameters, leaving the agent with insufficient context for 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 description mentions only 2 of 7 parameters ('language', 'filePath'), leaving 'tags', 'maxRules', 'matchMode', 'projectId', and 'fileContent' completely unexplained. Schema description coverage is 0%, so the description must compensate but fails to add any semantic value for the majority of parameters.

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 'query' and resource 'rules' along with key parameters 'language' and 'filePath', making the basic purpose clear. However, it does not differentiate from the sibling 'list_rules' and does not clarify what 'query' entails (e.g., filtering vs. retrieving).

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 'list_rules' or 'cognition_query'. There are no hints about prerequisites, use cases, 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?

No annotations exist, so the description bears full responsibility for disclosing behavioral traits. The phrase 'resolve a rule conflict' implies a mutation, but the description fails to state whether it alters state, requires permissions, or is reversible, making it poorly 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?

The description is a single short sentence, which is concise but under-specified. It lacks essential information, making it more of an underspecification than efficient conciseness.

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 three parameters, no output schema, and no annotations, the description is extremely incomplete. It fails to provide sufficient context for an agent to use the tool correctly, as none of the parameters or their roles are explained.

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 0%, and the description adds no information about the three parameters (conflictId, resolution, batchAllSession). The enum values in resolution are not explained, which is critical for correct invocation.

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?

Description states 'resolve a rule conflict', which is a verb+resource but lacks specificity. It is clear enough to distinguish from siblings like 'confirm_rule' or 'capture_diff', but does not elaborate on what resolving entails, making it vague.

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 prerequisites, exclusions, or context, leaving the agent to infer usage from the name alone.

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?

Annotations are missing, so the description bears full responsibility for behavioral disclosure. It states the tool 'sets or gets' but omits side effects: overwrite behavior, persistence, value limits, or required permissions. For a mutation-capable tool, this is insufficient.

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 achieves conciseness, but could be expanded slightly to cover key details without losing 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?

With no output schema, no annotations, and 0% schema coverage, the description is severely incomplete. It does not explain return values (for 'get'), error conditions, or behavior for missing keys. A tool with 4 parameters requires more contextual detail for 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?

Schema description coverage is 0%, so the description must compensate. It mentions 'set or get' and 'shared context value', hinting at key and value roles, but does not explain each parameter explicitly. For 'action' it alludes to enum values, but nothing about 'value' being required only for 'set', or that 'key' is the identifier. The description adds minimal meaning beyond the raw 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: 'Set or get a shared context value within a session'. It uses a specific verb (set/get) and resource (shared context value). It distinguishes from sibling session management tools (create, join, leave, etc.) which deal with session lifecycle, not intra-session 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?

No explicit guidance on when to use this tool versus alternatives. It does not mention prerequisites (e.g., session must exist via session_create) or when to use get vs set. The action parameter implies usage, but the description lacks context for an AI agent to decide 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?

No annotations provided; description carries full burden but only states 'create'. Does not disclose side effects, authentication needs, idempotency, or behavior with duplicates.

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?

Single sentence of 10 words is very concise but lacks essential details. Front-loaded with action but is under-specified for a 5-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 5 parameters (1 nested object), no output schema, and no annotations, the description is severely incomplete. No return value, error conditions, or session lifecycle context provided.

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 0% and the description adds no information about the five parameters. Agent must guess semantics of name, ttlMs, projectId, creatorName, and initialContext.

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?

Description clearly states the verb 'Create', the resource 'session', and the purpose 'for multi-turn governance workflows'. It distinctively labels this as the creation operation among sibling session 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?

No guidance on when to use this tool vs alternatives like session_join or session_status. Does not specify prerequisites or context for creation.

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 'Join an existing collaborative session' without disclosing behavioral details like permissions, side effects, or error handling, which are critical 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, which is concise but too brief to be fully informative; it could include more detail without becoming 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?

With 3 parameters, no output schema, and no annotations, the description is insufficient. It does not cover return values, how to obtain sessionId, or role implications, making it incomplete for an agent to use 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?

The schema has 0% parameter description coverage, and the description does not explain the meaning of parameters (e.g., role options, sessionId format), leaving the agent without necessary guidance.

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 'Join an existing collaborative session' clearly states the verb 'join' and the resource 'existing collaborative session', distinguishing it from siblings like session_create (create) and session_leave (leave).

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 vs alternatives, such as preconditions (session must exist) or when not to use (e.g., to create a session, use session_create).

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 full burden. It only states 'leave' without disclosing side effects (e.g., whether the session is closed, if other participants are notified, or if resources are released).

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 extremely short but under-specified. It sacrifices completeness for brevity, lacking sufficient detail to guide tool usage.

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, no annotations, and minimal description, the tool is severely incomplete. The agent lacks critical context about input validation, return values, and behavioral 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?

Schema description coverage is 0%, and the description adds no information about the 'sessionId' or 'participantName' parameters, failing to clarify their format or purpose.

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 (leave) and the resource (collaborative session), making the purpose unambiguous. However, it does not differentiate from sibling tools like session_join or session_create beyond the verb.

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 alternatives (e.g., session_status, session_list). It lacks context about prerequisites or post-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?

No annotations are provided, so the description must carry the full burden. It indicates a read operation ('List') but does not disclose return format, pagination, or what constitutes 'active'. Minimal 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?

Single sentence that is front-loaded and contains no superfluous words. Every part 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?

Covers the basic function but lacks details on return values (no output schema) and definition of 'active'. Could be more informative given the absence of annotations and 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 0%, so the description compensates partially by stating 'optionally filtered by project', linking projectId to filtering. However, it adds no details on value format or constraints beyond the schema's type string.

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 all active sessions with an optional project filter. It distinguishes from sibling tools like session_create, session_join, etc., which are for creating or joining sessions.

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 explicit guidance on when to use this tool versus alternatives. The context is clear from sibling tool names, but no exclusions or conditions 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, the description carries full burden. It mentions optional history retrieval but omits behavioral details such as authentication needs, rate limits, side effects, or what happens when the session 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 concise sentence with no redundant words. However, it lacks structure for multiple parameters and could benefit from bullet points or clearer separation.

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?

No output schema exists, so description should explain return values. It lists 'session details, participants, context, and optionally tool call history' but is vague. Missing error conditions, pagination hints, and field descriptions makes the tool incomplete for an 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 coverage is 0%, so description must explain parameters. It only hints at includeHistory via 'optionally tool call history' but does not describe sessionId, historyLimit, or their formats. Nearly all parameter meaning relies solely on schema names, which is insufficient.

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 'Get session details, participants, context' which clearly indicates a read operation on a session resource. It distinguishes itself from sibling tools like session_create or session_join, but is vague compared to session_context which may have a narrower 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 versus alternatives like session_list or session_context. No prerequisites, exclusions, or context are mentioned, 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?

No annotations are provided, so the description carries full burden. It implies a read-only operation ('List'), but does not explicitly state that no modifications occur, auth requirements, or any other behavioral traits. For a simple list, this is minimally adequate but lacks full 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 a single sentence of six words, with no wasted content. Every word earns its place, and the most important information is front-loaded.

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 no parameters, no output schema, and no annotations, the description sufficiently states what the tool does. It could elaborate on the format of the returned data, but the current level is adequate for a simple list.

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 zero parameters, so schema description coverage is 100%. According to guidelines, baseline for 0 parameters is 4. The description adds no parameter-specific information, but none is needed.

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 'List all registered webhooks and delivery statistics' clearly states the verb (List) and resource (registered webhooks), and includes the additional detail 'delivery statistics', which distinguishes it from siblings like webhook_register or webhook_test.

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 to use this tool: to retrieve all registered webhooks and their delivery statistics. It does not explicitly state when not to use it or provide alternatives, but the purpose is straightforward and no major ambiguity exists given the 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?

No annotations are provided, so the description must cover behavioral traits, but it only states a simple action. Missing details on idempotency, error handling, authentication requirements, or 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 sentence, front-loaded with the core purpose. It is concise but could include more meaningful details without becoming 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?

With 4 parameters, no output schema, and no annotations, the description lacks information on return values, parameter constraints, and setup requirements, leaving gaps for an 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?

The input schema has 4 parameters with 0% description coverage, and the tool description adds no explanation for individual parameters beyond their names. The 'secret' and 'projectId' fields are not clarified.

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 ('Register a webhook URL') and the purpose ('to receive governance events') with examples of events. It distinguishes from sibling tools like webhook_unregister and webhook_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?

The description implies usage for setting up event notifications but provides no explicit guidance on when to use this tool versus alternatives, nor any prerequisites 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?

The description discloses the basic behavior (test ping to verify connectivity) but lacks details on expected response, authentication, or error handling. With no annotations, more disclosure is needed.

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 essential action and purpose without extraneous 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 low-complexity tool with one parameter and no output schema, the description is minimally adequate but lacks parameter details that would help the agent use 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?

The sole parameter 'webhookId' has no description in the schema (0% coverage) and the tool description provides no context about its format, source, or how to obtain it. This leaves the agent guessing.

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 ('send a test ping'), the target ('registered webhook'), and the objective ('verify connectivity'). It effectively distinguishes from sibling tools like webhook_register and webhook_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?

While the purpose is clear, no explicit guidance is given on when to use this tool versus alternatives, nor are there any prerequisites or post-conditions 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?

No annotations provided, so the description carries the burden. It discloses the destructive nature of the action, but lacks details on side effects, authentication, or error conditions. Adequate for a straightforward removal.

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 sentence with no wasted words, directly conveying the purpose. Perfectly 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 tool with one parameter and no output schema, the description is sufficient to understand the core action. Could mention error cases, but overall complete for a simple unregister 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 description mentions 'by ID' which hints at the parameter's role, but schema coverage is 0% and no additional info is given about the webhookId format or how to obtain it. Minimal 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 verb 'Remove' and the resource 'registered webhook by ID', making the purpose specific and distinguishable from siblings like webhook_register and webhook_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 explicit guidance on when to use or when not to use this tool, but the purpose is clear and sibling tools provide context for alternatives. A simple tool with implied usage.

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