Server Quality Checklist

Tool Scores

• get_api_by_pathA
  3.8/5.0
  Behavior4/5

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

  Annotations already indicate read-only, idempotent, non-destructive, and open-world hints. The description adds real-time query behavior and return structure (schemaTree, flatFields), plus a disclosure requirement. No contradiction.

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

  Conciseness5/5

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

  Two sentences, no waste. Purpose and key details (real-time, schemaTree, flatFields, sourceNotice) are front-loaded.

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

  Completeness4/5

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

  With no output schema, the description covers return type (schemaTree, flatFields) and a behavioral rule. Given the tool's simplicity and annotations covering safety, it is sufficiently complete.

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

  Parameters3/5

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

  Schema covers all 4 parameters with descriptions (100% coverage). The description restates 'path' and 'method' but adds usage nuance (e.g., method optional if single, group optional if single group). This provides marginal extra value beyond the schema.

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

  Purpose5/5

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

  The description clearly states the tool's function: querying complete API documentation in real-time by exact path and optional HTTP method. It distinguishes from siblings by focusing on path-based lookup, whereas siblings like list_api_categories or search_apis serve different purposes.

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

  Usage Guidelines2/5

  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 vs alternatives (e.g., search_apis for fuzzy matching, inspect_api_docs for browsing). The description only mentions a presentation rule (retain sourceNotice) but not selection criteria.

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

• get_api_categoryA
  4/5.0
  Behavior4/5

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

  Annotations declare readOnlyHint=true, destructiveHint=false, etc. The description adds real-time behavior, exact matching, and a retention notice for sourceNotice, providing useful context beyond annotations.

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

  Conciseness4/5

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

  The description is short (two sentences) and efficiently conveys the tool's purpose. It could be slightly more structured but is concise and front-loaded.

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

  Completeness3/5

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

  With no output schema, the description omits return value details beyond summary/full. It notes sourceNotice retention, but a more detailed explanation of response structure would improve completeness for a tool with 6 parameters.

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

  Parameters4/5

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

  Schema coverage is 100% (all 6 parameters described). The description adds that 'summary' returns abstracts and 'full' returns request/response schemas, enhancing clarity beyond the schema's enum values.

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

  Purpose5/5

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

  The description clearly states the tool queries APIs by exact category name in real-time, with two detail levels (summary/full). It effectively distinguishes itself from sibling tools like list_api_categories and get_api_by_path.

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

  Usage Guidelines3/5

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

  The description mentions real-time querying and detail levels but does not provide explicit guidance on when to use this tool compared to alternatives like search_apis. No exclusions or prerequisites are mentioned.

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

• list_api_categoriesA
  4/5.0
  Behavior4/5

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

  The description reveals behavior beyond annotations: it operates in real-time, does not call business APIs, does not cache, and instructs the agent to retain sourceNotice in responses. Annotations already confirm read-only, idempotent, non-destructive nature. No contradictions.

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

  Conciseness5/5

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

  Three sentences, each serving a distinct purpose: first explains core function, second gives a user-reply instruction, third clarifies side-effect constraints. No fluff.

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

  Completeness4/5

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

  Given the simple nature and full annotations/schema, the description covers key aspects: real-time retrieval, no caching, no business API calls, and response handling. It does not explicitly mention pagination or what the output format includes, but the schema parameters imply pagination.

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

  Parameters3/5

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

  Schema coverage is 100%, so the description adds little new meaning. It restates the purpose from the docsUrl parameter description but does not elaborate on page, group, or pageSize beyond what the schema provides.

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

  Purpose5/5

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

  The description clearly states the tool reads a specified docsUrl and lists categories with interface counts. It distinguishes itself from sibling tools like get_api_category (single category) or search_apis (search) by focusing on listing all categories. The mention of not caching or calling business APIs further clarifies its scope.

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

  Usage Guidelines3/5

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

  The description does not explicitly state when to use this tool vs alternatives. It implies usage for obtaining a category overview, but lacks direct guidance on selecting this over inspect_api_docs or get_api_by_path.

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

• search_apisA
  4/5.0
  Behavior4/5

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

  Annotations already declare readOnly, idempotent, non-destructive hints. The description adds a behavioral note: '回答用户时必须明确保留 sourceNotice' (must keep sourceNotice when answering the user), which is critical for proper response handling. No contradictions with annotations.

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

  Conciseness5/5

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

  The description is two sentences with no wasted words. The first sentence provides the core purpose, and the second adds a specific usage instruction. It is concise and front-loaded.

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

  Completeness4/5

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

  For a search tool with 5 parameters (2 required) and no output schema, the description covers purpose, scope (real-time Swagger doc), and a behavioral requirement. It lacks a description of the return format or pagination details, but those are partially covered by schema. Overall, it is sufficiently complete for correct invocation.

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

  Parameters3/5

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

  Schema description coverage is 100%, so the schema already documents each parameter. The description does not add additional parameter-level semantics beyond the schema, maintaining the baseline of 3.

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

  Purpose5/5

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

  The description clearly states the verb '搜索' (search) and the resource 'Swagger 接口', and lists specific searchable fields (path, summary, description, tag, operationId). It also differentiates from sibling tools like inspect_api_docs or get_api_by_path by specifying that the search is across a real-time Swagger document.

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

  Usage Guidelines3/5

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

  The description implies usage when searching across Swagger APIs, but does not explicitly state when to use this tool versus alternatives like inspect_api_docs or list_api_categories. No explicit when-not or alternative guidance is provided.

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

• inspect_api_docsA
  4.3/5.0
  Behavior4/5

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

  Annotations already declare readOnlyHint=true, so description adds operational flow: returns candidates and nextAction, and specifies next steps. No contradiction. Adds useful context beyond annotations.

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

  Conciseness4/5

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

  Single paragraph, front-loaded with condition for calling. Clear and efficient, though could be slightly more concise.

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

  Completeness4/5

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

  No output schema, but description mentions return of candidates and nextAction, and covers when to call and next steps. Adequately complete for a read-only inspection tool.

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

  Parameters3/5

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

  Schema coverage is 100% (baseline 3). Description adds slight context by noting docsUrl should be complete address (doc.html or Swagger JSON), but no new semantics beyond schema.

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

  Purpose5/5

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

  Explicitly states it inspects Swagger doc URLs after user explicitly requests query/debug/search/list/analyze. Clearly distinguishes from siblings by focusing on doc inspection.

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

  Usage Guidelines5/5

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

  Provides explicit condition for calling (only after user expresses intent to query/debug/search/list/analyze) and warns against calling on isolated URLs. Gives clear context and exclusions.

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