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

With no annotations available, the description carries the full behavioral disclosure burden. It clearly reveals that sensitive field values are read from the service process environment variable at write time, that this is recommended to avoid secrets passing through conversation content, and that all fields are AES-256-GCM encrypted before being stored. These are meaningful security-relevant behaviors beyond what the schema conveys.

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 three short sentences with no filler. It front-loads the purpose, immediately adds the critical env-var pattern, and closes with the encryption guarantee. Every sentence contributes useful information.

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

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

Given the rich input schema, the description is largely complete for invocation: it covers the creation intent, uniqueness, secret handling, and persistence encryption. It does not describe return values or error behavior, and there is no output schema, but for a create operation these are not significant enough to lower the score further.

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 high (88%), so the baseline is 3. The description adds extra meaning by specifying that 'env:VAR_NAME' is resolved from the service process environment variable at write time, recommends this pattern for security, and notes that every field is encrypted at rest. These details enhance the semantics of the fields parameter beyond the schema's own explanation.

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

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

The description states a specific verb and resource: '添加一个系统凭据' (add a system credential), with a clear uniqueness constraint. It distinguishes itself from siblings like update_credential and delete_credential by the action 'add', though it does not explicitly name or contrast those alternatives.

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

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

The description gives no guidance on when to use add_credential versus update_credential, verify_login, get_token, or reveal_secret. It only implies creation by the word '添加' and suggests using 'env:VAR' for sensitive values, but does not state prerequisites, exclusions, or when to use an alternative.

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 behavioral burden. It explicitly discloses irreversibility and the pre-deletion usage-stats summary, which are important and non-obvious traits. However, it does not mention permission requirements, rate limits, or impact on dependent credentials/tokens.

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 short, front-loaded sentences convey the action, the critical irreversibility warning, and a notable behavioral detail. Every clause earns its place; there is no repetition of the tool name or schema.

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 adequately covers the input (via schema), the destructive nature, and the pre-deletion stats output. However, with no output schema and no annotations, it leaves gaps around the post-deletion response, success/failure behavior, and any required authorization.

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

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

The schema already provides 100% coverage with a clear description for the single 'name' parameter ('凭据名称或 id'). The tool description adds no additional parameter-level meaning, so the baseline score of 3 is appropriate.

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

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

The description uses a specific verb and resource: '删除一个凭据' (delete a credential), and adds a decisive qualifier '不可恢复' (irrecoverable). This clearly distinguishes it from sibling tools such as list_credentials, update_credential, and usage_stats.

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 explains what the tool does but gives no guidance on when to use it versus alternatives. Notably, it mentions returning usage statistics before deletion, which could mislead an agent into calling this destructive tool for stats alone; the sibling usage_stats is not referenced.

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

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

With no annotations provided, the description carries the full disclosure burden. It discloses that tokens are cached in memory, expire, and are automatically re-issued, plus the return payload (token value, header, validity). It does not mention error conditions or authorization requirements, but the core behavioral traits are well-covered.

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

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

The description is two concise sentences, front-loaded with the core function and purpose requirement. Every clause earns its place, and the return details are compactly listed. No fluff.

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 3 parameters and no output schema, the description adequately covers the return value, caching, and expiration. It does not explain error scenarios or token scope, but for a token issuance tool the essentials are present. Slightly more detail on error handling would elevate it, but it's complete enough for an agent to invoke correctly.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by explaining the purpose parameter's audit purpose and implying the refresh behavior via '或复用缓存的' (or reuse cached). It also describes the return format, enriching the schema without repeating it.

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

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

The description clearly states the verb '签发/复用' (issue/reuse) and the resource '凭据' (credential), explicitly distinguishing it as a token provisioning tool. It also mentions the purpose requirement and return format, which separates it from sibling tools like verify_login or list_credentials.

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

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

The description implies when to use it: when a temporary token is needed for subsequent calls. It explicitly requires a purpose for audit, which is a clear precondition. However, it does not name alternative tools or exclusion conditions, though the context makes it obvious this is the go-to for token acquisition.

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

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

With no annotations provided, the description carries the full behavioral burden. It usefully discloses that the tool lists metadata only and explicitly does not return secret plaintext, which is critical for an agent to avoid misuse. It does not mention pagination, ordering, or error behavior, but for a zero-parameter list operation the key safety and scope behaviors are covered.

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 compact and front-loaded: the first sentence states the operation and its output scope, and the second sentence adds a crucial safety warning plus a concrete usage directive. Every sentence earns its place with no filler.

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

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

Given the tool's low complexity (no parameters) and the absence of an output schema, the description provides sufficient information: what metadata is returned, what is not returned, and when to use it. It could mention pagination or return formatting, but these are minor gaps for a credential-listing operation that the agent can call without extra input.

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 zero parameters, and the schema description coverage is 100% (trivially, since there are no properties). The baseline for zero parameters is 4, and the description appropriately adds no unnecessary parameter information that would be irrelevant.

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

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

The description states a specific verb ('list') with a clear resource ('all credential metadata') and enumerates the exact metadata fields returned (name, system, type, field name, endpoint configuration). It also explicitly distinguishes itself from secret-returning tools by noting it returns no plaintext secrets, which differentiates it from siblings like reveal_secret and get_token.

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 explicit guidance to call this tool before add/get_token to confirm credential names. It does not explicitly name alternatives for retrieving actual secrets, but the statement that it returns no plaintext secrets implies when this tool is not appropriate, giving the agent adequate context for routing.

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 and provides meaningful behavior: it starts or reuses a local console, returns a one-time access token URL, and binds only to 127.0.0.1. It does not mention process lifecycle or token expiry, but the key side effects and security scoping are disclosed.

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

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

Two sentences, front-loaded with the core action and return value. The second sentence lists GUI capabilities, which helps an agent decide between this tool and the sibling CLI-style tools, though the list is slightly enumerative.

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 tool with no output schema, it explains the return value (access URL with one-time token), the localhost binding, and the invocation trigger. Minor gaps remain around prerequisites and lifecycle/cleanup, but an agent has enough to select and call 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 tool has zero parameters, so the baseline is 4. The description adds no parameter-level details, and none are 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?

States a specific action and resource: 启动（或复用）mkeys 本地 Web 管理台并返回带一次性访问令牌的访问地址. It clearly distinguishes itself from the sibling credential/verification tools by positioning itself as the GUI admin surface rather than a programmatic operation.

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?

Explicitly gives trigger conditions: 用户说'打开/看 mkeys 管理页面'或需要图形界面管理凭据时调用. It does not explicitly name alternatives or when-not cases, but the contrast with the programmatic sibling tools is clear enough.

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

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

With no annotations provided, the description carries the full burden and does so exceptionally: it flags the operation as dangerous, states that every call is audit-logged, and discloses it is disabled by default with a required setting. This goes beyond a typical mutation warning and gives the agent actionable safety 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?

Two concise sentences front-load the danger and audit behavior, then state the enablement requirement and the alternative tool. Every clause earns its place with no filler or repetition.

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

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

The description covers safety, enablement, and tool selection well, but leaves gaps for a dangerous no-annotation tool: it does not describe the return value (the plaintext secret), what name precisely identifies, or what purpose is expected for the audit log. Given the high risk and low schema coverage, more operational detail would be needed for fully confident invocation.

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

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

The schema covers only one of three parameters (field), and the description adds no parameter-specific meaning for name or purpose. It does not clarify what name refers to or what should be supplied for purpose, leaving the agent to infer from sibling context. With 33% coverage, the description should compensate but does not.

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

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

The description states a specific verb and resource: reading the raw plaintext of credential secrets. It explicitly contrasts with get_token, distinguishing this tool from the closest sibling and making its unique role clear.

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

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

It provides explicit when-not-to-use guidance by stating that get_token should be preferred for temporary tokens, and it gives a prerequisite condition: the allowReveal setting must be enabled. This leaves no ambiguity about when the 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?

With no annotations provided, the description carries the full behavioral burden. It discloses non-obvious behavior: fields are merged by key, removeFields deletes fields, endpoints are replaced wholesale, and env:VAR indirection is supported. This goes beyond the schema and warns about destructive/replacement semantics.

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 the purpose front-loaded and the key behavioral rules compactly listed. There is no filler or redundant restating of schema fields.

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 10-parameter mutation tool with no output schema and no annotations, the description covers core update semantics but omits behavior for several parameters and does not explain what happens to unspecified fields. It is useful but not fully complete for every calling scenario.

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 only 20%, so the description must compensate. It adds valuable semantics for the most nuanced parameters: fields (merge), removeFields (delete), endpoints (replace), and env:VAR references. However, it leaves tags, system, newName, authType, ttlSeconds, and description to self-explanatory names or the schema enum, so compensation is only partial.

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

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

The description opens with '更新已有凭据' (update existing credential), naming a specific verb and resource, and the 'existing' qualifier distinguishes it from add_credential and delete_credential. It also states concrete update behaviors (merge, remove, replace), so an agent can clearly identify this tool's role among siblings.

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

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

The description clearly establishes that this tool is for modifying an existing credential, which tells an agent when to select it over add_credential or delete_credential. It does not explicitly name alternatives or list when-not-to-use conditions, but the context is unambiguous.

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

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

With no annotations, the description carries the burden of explaining behavior. It communicates read-only semantics through '查询' and details what the tool returns: call volume, success rate by credential/purpose/day, and recent failure records. It does not discuss permissions or data retention, but for a non-destructive statistics query this is reasonably complete.

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 compact sentences: the first states what the tool does and its output dimensions, the second gives concrete invocation triggers. There is no filler or redundant restating of schema fields.

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, the description compensates reasonably by naming the main result dimensions and failure records. It does not specify the exact response shape or pagination, but for a statistics query with simple filter parameters this is enough for an agent to call it correctly in the stated scenarios.

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 the schema already documents all four parameters with types, defaults, and ranges. The description loosely maps to the parameters (credential, purpose, day) but adds no syntax or format detail beyond the schema, so the 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 names a specific resource ('AI 使用统计') with a clear query verb and enumerates the breakdown dimensions: by credential, purpose, and day, plus success rate and recent failures. It also gives concrete user-phrase triggers ('密钥用了多少次/用在哪/用来干什么'), which distinguishes it from the credential-management sibling tools.

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

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

The description explicitly states when to invoke the tool: when the user asks how many times a key was used, where it was used, or what it was used for. It does not explicitly list exclusions or alternatives, but the sibling tools are all credential CRUD/management actions, so the analytics use case is already clearly differentiated.

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 behavioral burden. It discloses the validation logic, HTTP status meaning, the fallback to token issuance, and that verification affects usage statistics. It stops short of stating side effects or permissions, but is substantially 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?

Three short sentences, each adding distinct information: what is verified, how it is determined, and the side-effect on usage stats. There is no repetition or filler.

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

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

For a one-parameter tool with no output schema, the description covers the key behavior and result interpretation. The only notable omission is the exact return value/format, but the 2xx/401/403 framing largely covers what an agent needs.

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% and the only parameter already has a description ('credential name or id'). The tool description adds no additional parameter-level meaning, so it meets the baseline without exceeding it.

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

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

The description clearly states the action (verify), the resource (credential login), and the exact success criteria (2xx valid, 401/403 rejected). This differentiates it from siblings like get_token or reveal_secret, 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 is given for when to choose verify_login over siblings such as get_token or list_credentials. The mention of preferring a configured verify endpoint is implementation behavior, not usage context or exclusions.

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