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

No annotations exist, so description must carry full burden. It mentions storage of patterns but does not disclose side effects (e.g., overwriting existing patterns), permissions needed, or any destructive potential.

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, no redundant words, front-loaded with the main action. Every sentence adds value.

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, so description should explain return values or effects. It does not. Also lacks error conditions, authentication needs, or data retention details.

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 description adds no extra meaning beyond what the parameter descriptions already provide. 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 verb 'extract' and resource 'memory patterns from a conversation', and mentions storing patterns. It is distinct from sibling tools like memory_recall (retrieve) and memory_reinforce (strengthen), but 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 guidance on when to use this tool vs. siblings. No exclusions or prerequisites are provided, 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?

No annotations. Description implies read-only health check but omits details like authentication, rate limits, or return format. Adequate but shallow.

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 redundancy, front-loaded. Efficient for a simple health-check 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?

No output schema, low complexity. Covers essential purpose. Minor gap: no indication of HTTP status codes or response structure.

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. Description adds nothing beyond schema (empty). Baseline 4 for 0 params; no improvement 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?

Clear verb 'Check' and resource 'Kova Mind API health'. Distinguishes from sibling memory and vault tools which handle data operations.

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 (e.g., before other calls) or alternatives. Does not mention context like availability checks.

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 does not mention whether the operation is read-only, any authorization needs, rate limits, or side effects. The description is purely functional.

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 wasted words. Front-loaded with purpose and usage context.

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 4 parameters, no output schema, and a short description. Missing information includes return format of memory patterns and how context influences recall. Adequate for a simple retrieval tool 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?

All parameters have schema descriptions, so baseline is 3. The description adds minimal context (e.g., 'natural language context') but does not explain how min_confidence affects results or how max_patterns interacts. No significant added value beyond 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 'retrieve' and the resource 'memory patterns', and specifies the use case of recalling what you know about a user. This distinguishes it from siblings like memory_extract or memory_reinforce.

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 a general when-to-use ('recall what you know about a user') but does not explicitly exclude alternatives like memory_extract for extracting patterns from text. No comparison with siblings 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?

No annotations provided, so description carries full burden. It discloses the action types (reinforce/deny) but lacks details on side effects, reversibility, or permissions. The description is functional but not highly transparent about internal 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?

Two sentences, front-loaded with purpose and immediate usage instructions. Every sentence adds value; no redundant or verbose content.

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?

Lacks output schema, but description does not explain return values or effects. It covers parameter usage adequately but omits context like required permissions, side effects, or what happens after reinforcement. For a tool with 3 params and an enum, it is moderately 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 covers all 3 parameters with descriptions. The description adds contextual guidance for reinforcement_type (confirmed vs denied), which goes beyond the enum labels. However, it does not elaborate on pattern_id or context parameters beyond 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?

Description clearly states the tool reinforces or denies a stored memory pattern, using specific verbs (reinforce, deny) and resource (memory pattern). It distinguishes from sibling tools like memory_recall or memory_extract by focusing on modifying confidence/status.

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?

Provides explicit guidance for the reinforcement_type parameter: 'Use confirmed when the user validates a memory, denied when they contradict it.' This helps the agent choose appropriate values, though it doesn't discuss when to use this tool over siblings or 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?

With no annotations, the description carries full burden for behavioral disclosure. It mentions novelty scoring and contradictions but does not detail side effects, authentication needs, rate limits, or what happens if memories are absent. The output format is unspecified.

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, efficient sentence that front-loads the action ('Score') and clearly states purpose and output interpretation. 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?

Despite no output schema, the description does not specify the return format (e.g., numeric score, range). It also lacks prerequisites (e.g., that memories must exist). The tool's relation to sibling memory tools is implied but not clarified.

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 context for 'content' by linking it to novelty evaluation, but the schema already describes it similarly. It does not mention 'user_id', which is documented in schema defaults. Minimal added value.

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 it scores novelty/surprise of new content relative to existing memories, using specific verbs and resource. It distinguishes from sibling tools like memory_recall (which retrieves memories) and memory_extract (which extracts entities) by focusing on novelty evaluation.

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 a clear use case: evaluating novelty. It implies when to use but does not provide explicit when-not or mention alternatives like memory_recall for retrieving similar memories. The high scores indication helps but lacks exclusion 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?

The description discloses that credentials are never exposed and flow through a secure side channel, which is critical. However, it omits other behavioral traits like error handling, idempotency, or required permissions. Since no annotations exist, the description should cover more.

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, using only two sentences to convey the purpose and a key security property. Every word adds value, and it 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?

With no output schema and 5 parameters, the description fails to explain return values or clarify the usage pattern for handle vs auto_detect. More context is needed for a first-time user.

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?

All parameters have descriptions in the schema (100% coverage), so the description adds minimal semantic value. It hints at the relationship between handle and auto_detect but does not explicitly state they are mutually exclusive.

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 executes an action using a credential, distinguishing it from other vault tools like vault_find or vault_store. However, it does not explicitly differentiate from memory tools or provide a broader 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 guidance is given on when to use this tool versus alternatives, such as when to prefer auto_detect over handle, or prerequisites like needing a handle from vault_handles.

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. It discloses that the tool returns matching handles with relevance scores and that credential values are never exposed. This gives clear behavioral expectations. Additional details like whether the vault must be unlocked or side effects are absent, but the core behavior is well communicated.

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 concise sentences with no wasted words. The first sentence gives the primary purpose, the second adds essential constraints. This is ideally front-loaded and minimal.

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 search tool with one parameter and no output schema, the description sufficiently covers what the tool does, what it returns, and a key limitation. It is complete enough for an agent to select this tool correctly. A minor gap is not mentioning prerequisites like vault state (locked/unlocked), but it's still effective.

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 already describes the 'query' parameter with examples. The description adds no further semantic detail about parameters; it only restates the purpose. Baseline 3 is appropriate as the schema does the heavy lifting.

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 finds credentials matching a search query, which is a specific action on a resource. It distinguishes from sibling vault tools like vault_handles (list handles) and vault_store (store) by focusing on search and explicitly noting it does not return credential values.

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 this tool by stating it returns handles with relevance scores and explicitly says 'You will never see credential values.' This guides the agent to use vault_find for discovery and use another tool (e.g., vault_execute) for obtaining values. However, it does not name alternatives or provide explicit when-not-to-use 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 are provided, so the description carries the full burden. It discloses that credential values are never shown, which is a key behavioral constraint. However, it does not mention privacy or security implications beyond that.

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 consists of two sentences that are front-loaded and to the point. Every sentence adds value, 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?

Given the simplicity of the tool (no parameters, no output schema), the description is adequate but lacks details on return format or any filtering capabilities. For a list tool, it could mention if results are paginated or sorted.

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 tool has no parameters, so schema coverage is 100% by default. The description adds no parameter info, which is acceptable given the lack of parameters. Baseline for 0 parameters is 4.

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 available credential handles' and specifies the resource. It distinguishes from sibling tools by noting that credential values are never shown, only handles, labels, and types.

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 is for listing handles, but does not explicitly state when to use it versus alternatives like vault_find or vault_store. No exclusions or context for 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?

Discloses critical behavior 'Zeros the encryption key from memory' despite no annotations. Lacks detail on consequences like loss of access or re-authentication needs.

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 concise sentences, front-loaded purpose, 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?

Sufficient for 0-param tool without output schema. Could mention reversibility but not required.

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?

Zero parameters – baseline 4 applies. No parameter info 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?

Clearly states verb 'Lock' and resource 'secrets vault', with behavioral detail 'Zeros the encryption key from memory'. Distinguishes from siblings like vault_unlock.

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?

Implies use for securing vault but no explicit when/when-not guidance or alternatives compared to 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 carries the full burden. It discloses that the tool returns 12 recovery words to be stored safely, and that the vault stores credentials agents can use without seeing values. This provides useful behavioral context beyond the parameter 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 only two sentences, front-loaded with the purpose, and contains no extraneous information. Every sentence adds value.

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) and the description's mention of the return value (12 recovery words) and security context, it is fairly complete. However, it could clarify whether calling it again is possible or what happens on re-execution.

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 parameter 'passphrase' already described in the schema (minLength 8). The description adds no additional meaning about this parameter, so it meets the baseline but does not go beyond.

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 'Set up the secrets vault for the first time,' which is a specific verb+resource action. It is easily distinguishable from sibling tools that deal with other vault operations (e.g., vault_execute, vault_store).

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 explicitly says 'for the first time,' indicating that this tool is intended for initial setup only. Although it does not explicitly state when not to use it, the context implies a one-time use and the sibling tools cover other 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 are provided, so the description must carry the full burden. It discloses that credentials are not returned and only an opaque handle is provided, which is crucial. However, it lacks detail on persistence, authentication 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?

The description is a single, front-loaded sentence that efficiently conveys the core purpose and a key behavioral trait. 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?

The description covers the essential aspects: what the tool does, how it behaves (opaque handle), and the return type. Given moderate complexity and no output schema, it is mostly complete, though it could mention that fields are stored securely.

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 already documents all parameters. The description does not add additional meaning beyond what is in the schema (e.g., format constraints or relationships).

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 (store), resource (credential in the vault), and a key behavioral trait (returns opaque handle, values never seen). This distinguishes it from sibling tools like vault_find (search) and vault_execute (execute).

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 provide explicit guidance on when to use this tool versus alternatives (e.g., vault_find for retrieval, vault_execute for using credentials). Given the presence of many sibling tools, such guidance would be valuable.

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 states the tool unlocks the vault with a passphrase, but does not describe failure modes (e.g., wrong passphrase), timeout, or side effects. The behavioral context is minimal but sufficient for a simple unlock 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 one sentence that front-loads the verb 'Unlock' and clearly states the purpose. It contains no extraneous words and efficiently conveys the tool's 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?

Given the simple nature of the tool (one required parameter, no output schema, no annotations), the description is largely complete. It explains the action and prerequisite relationship. However, it could explicitly note that the vault remains unlocked until vault_lock is called for better 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 for the single parameter 'passphrase' is 100%, and the schema itself describes it as 'Vault passphrase'. The description adds no additional meaning beyond what the schema provides, earning a 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 action (unlock) and the resource (secrets vault), and specifies it is required before storing or using credentials, distinguishing it from sibling tools like vault_lock (which locks) and vault_store (which requires prior unlock).

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 indicates when to use this tool ('Required before storing or using credentials'), providing clear context for its necessity. It does not explicitly state when not to use or describe alternatives, but the sibling names imply vault_lock is the inverse, and the need before other operations is clear.

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