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 offers no behavioral context beyond restating the function—no mention of read-only nature, path limits, or result structure. It is essentially a tautology.

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 redundancy. It is front-loaded and appropriately sized for a simple tool, though it lacks supporting details that would make it more 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 no output schema and sparse annotations, the description leaves significant gaps: it does not describe the return format, error behavior, or how it differs from getting a single API detail. The tool is simple, but the description is too thin to be complete.

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

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

The schema description coverage is 100% for the single parameter 'paths', which is described as an array of interface paths. The description adds no additional semantics, so the baseline of 3 applies.

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

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

The description clearly states the tool performs a batch retrieval of detailed information for multiple APIs, using the specific verb '批量获取' and resource '多个接口的详细信息'. It distinguishes from get_api_detail which is singular, though it does not name alternatives explicitly.

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

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

No guidance is provided on when to use this tool versus alternatives like get_api_detail or smart_search_api. The batch nature is implied but there are no explicit exclusions or context for choosing this tool.

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

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

With no annotations, the description carries the full burden. It discloses that omitting method returns all methods for the path, and lists the returned content (参数/请求体/响应/示例). However, it doesn't mention errors or auth prerequisites, though the key behavioral nuance of the optional method is 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 concise and structured: a one-sentence purpose followed by three clear bullets. Every sentence adds value, the main purpose is front-loaded, and there is 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?

For a tool with 2 params, no output schema, and no annotations, the description covers core functionality, workflow with search_api, and optional method behavior. It could elaborate on response structure beyond listing content types, but it is sufficiently complete for a single-interface retrieval 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 coverage is 100% for both parameters, so baseline is 3. The description restates the optionality of method and the role of path, but adds little beyond schema. The note about using with search_api is more workflow than parameter semantics.

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 retrieves complete documentation for a single API endpoint ('获取单个接口的完整文档'). It distinguishes itself from siblings by positioning it as the precise follow-up to search_api and emphasizing '单个' (single), contrasting with batch_get_apis.

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?

A dedicated '使用指引' section gives explicit when-to-use instructions: direct use when path is known, use after search_api for precise details, and explains the optional method behavior. This clearly delineates the workflow and 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 transparency burden. It adds valuable behavioral context: 'only returns summary information' and implicitly indicates a read-only listing operation. It does not cover auth, pagination, or error behavior, but those are less critical for a simple non-mutating list 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 that is front-loaded with the core action and resource, followed by a clarifying caveat about summary data. There is no waste or redundancy.

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 with no output schema, the description adequately explains the return value (paths and methods, summary only). It lacks details like pagination or limit behavior, but the simplicity of the tool makes this likely sufficient.

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 is empty (0 parameters), so schema coverage is effectively 100%. Per guidelines, zero-parameter tools get a baseline score of 4; the description does not need to elaborate on 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 clearly states a specific action (list) and resource (all endpoints), further specifying the returned content (paths and methods) and scope (summary only). This distinguishes it from siblings like get_api_detail (details), list_api_by_tag (filtered), and list_api_by_folder (filtered).

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

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

The phrase 'all endpoints' implies use when a complete, unfiltered list is needed, and the summary-info note suggests it's a lightweight overview. However, it does not explicitly mention alternatives or when not to use this tool compared to search/filter siblings.

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

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

With no annotations, the description carries the full burden. It discloses the filtering behavior and matching modes (exact and fuzzy), which is useful. However, it does not describe the return format, potential pagination, error behavior, or whether results are sorted or nested, leaving gaps for a read-only listing tool.

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

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

The description is a single concise sentence that front-loads the primary action (filter by folder path) and immediately adds the matching behavior. No redundant or extraneous text.

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

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

The tool is simple (1 parameter, no output schema), and the description covers the core functionality and matching behavior. However, since there is no output schema, the description could have noted the return format or any limitations, but it does not, leaving some ambiguity for a complete understanding.

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

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

The schema description covers the folder parameter well (100% coverage), but the tool description adds value by specifying that matching supports exact and fuzzy modes, which clarifies how the 'folder' string is interpreted beyond the schema's example values.

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 filters an API list by Apofox folder path, using the verb '筛选' (filter) and the resource '接口列表' (API list). This distinguishes it from siblings like list_api_by_tag (filter by tag) and list_api_folders (list folders), making its purpose immediately apparent.

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 implies the tool is used when you want to filter APIs by folder path, with support for exact and fuzzy matching. It does not explicitly name alternatives, but the folder-path focus provides clear contextual guidance without exclusions.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. However, '按标签筛选接口列表' essentially restates the tool's name and adds no information about return format, match semantics, data scoping, or errors. It provides minimal additional behavioral context.

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

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

The description is a single, front-loaded sentence that is not verbose and efficiently conveys the core action. However, it is extremely brief and does not include any additional structured context, so it earns a 4 rather than a 5.

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

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

For a simple tool with one parameter and no output schema, the description is adequate but incomplete: it omits any mention of the return value shape, whether matching is exact or partial, and does not point to alternatives. Without annotations, the description should at least hint at output behavior, but it does not.

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

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

The input schema has 100% description coverage for the single parameter 'tag' (description: '要筛选的标签名称'), so the baseline is 3. The description's 'by tag' adds nothing beyond what the schema already states, such as format, examples, or edge cases.

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 '按标签筛选接口列表' clearly identifies the action (filter), the resource (API list), and the specific criterion (by tag). This distinguishes it from sibling tools like list_api_by_folder and search_api, which target different dimensions or capabilities.

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

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

The description implies when to use the tool (when you need APIs filtered by tag) but does not explicitly say when to prefer it over alternatives like smart_search_api or list_api_by_folder. No exclusions or fallback scenarios are mentioned, leaving the usage guidance only implicit.

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 does not disclose whether the operation is read-only, does not describe the return structure or pagination, and provides no information about authentication or side effects. The description adds minimal behavioral context beyond what the tool name implies.

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

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

The description is a single, concise sentence that immediately states the tool's purpose. Every word contributes value, with no filler or redundancy.

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 (zero parameters, no output schema), the description provides sufficient context for its core function. It fully explains what the tool does, and the absence of output details is acceptable for a simple listing 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 tool has zero parameters, so the baseline is 4 per the rubric. The empty input schema is fully covered, and there is nothing for the description to add regarding parameter semantics.

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 Apifox folder directory structures, using a specific verb ('list') and resource ('Apifox folders'). It distinguishes itself from sibling tools like list_api_by_folder, which likely lists APIs within a folder rather than the folders themselves.

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

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

The usage context is implied: one would use this tool when needing an overview of the folder hierarchy. However, it does not explicitly mention when to use it over alternatives or provide exclusions, so it lacks the explicit guidance of higher-scoring examples.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states the refresh action and data source, but does not disclose side effects like cache overwriting, network dependencies, or the existence of a cooldown mechanism (though hinted by the force parameter).

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 efficiently communicates the core purpose and source without redundancy.

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 optional parameter, no output schema), the description is minimally adequate. However, it omits any mention of cooldown/force behavior and potential side effects, which would be useful for complete context. The schema fills in the parameter gap, but overall completeness is moderate.

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

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

Schema description coverage is 100% with the single 'force' parameter clearly described in the schema. The description itself adds no parameter-level detail, but the schema already provides sufficient semantics, justifying the baseline score of 3.

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

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

The description clearly states the tool refreshes the interface cache and re-fetches latest data from Apifox. This distinct verb+resource combination sets it apart from sibling tools that are all search/list 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?

The description implies usage for updating stale cache but does not explicitly state when to use it or provide alternatives/exclusions. There is no mention of cooldown or when the force parameter should be used, leaving the agent to infer from the schema.

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

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

With no annotations, the description carries the full burden. It discloses matching modes (exact, wildcard, fuzzy, path segment) with concrete examples like '/api/users/*' and 'daren/influencer', which is substantive behavioral information beyond the schema. However, it does not mention case sensitivity, pagination, error behavior, or result format, leaving some gaps.

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

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

The description is well-structured with bullets and front-loaded purpose, making it easy to scan. It is slightly longer than minimal but every section (use cases, matching modes) adds necessary guidance. No redundant sentences found.

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

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

The tool is simple (1 parameter, no output schema, no annotations), but the description provides solid use-case triggers and matching behavior. However, it does not describe what the tool returns or its limitations (e.g., no results, ordering, pagination), and it fails to distinguish itself from smart_search_api. Given no output schema, some return-value context would complete the picture.

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 covers the single parameter 'pattern' with a clear description, and schema coverage is 100%. The tool description adds extra value by enumerating specific matching modes and examples, enriching the meaning of the parameter beyond the schema's generic definition.

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

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

The description clearly states the tool's function: searching APIs by URL pattern, and calls itself the preferred tool for finding APIs. It distinguishes from list-by-tag/folder sibling tools by focusing on URL patterns, but does not explicitly contrast with smart_search_api, so sibling differentiation is slightly incomplete.

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 explicit use cases: automatically call when the user mentions an API path/URL, when asking about a feature's API, and when needing to know a module's APIs. This gives clear context on when to use, but it does not mention exclusions or alternatives like smart_search_api, so it lacks explicit comparison with overlapping siblings.

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 must carry the burden. It discloses key behaviors: automatic keyword extraction, path mapping, mixed Chinese-English support, and relevance sorting. It does not discuss edge cases or output details, but for a simple search tool, this is sufficient 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 well-structured with clear sections (core capabilities, use cases, priority directive). It uses bullets and examples efficiently without fluff. Every sentence contributes to understanding the tool.

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

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

For a single-parameter tool with no output schema, this description is quite complete. It explains purpose, usage scenarios, behavioral mechanics, and next steps. It doesn't detail return format, but states relevance sorting, which adequately covers what the agent needs to know for 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 already defines 'query' as natural language, but the description adds meaningful examples and clarifies expected input types (e.g., '查找用户登录接口', '获取订单列表'). This goes beyond the schema's minimal description, giving the agent concrete grounding for what to provide.

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's an intelligent search tool that maps natural language queries to API paths, with explicit examples of query types. It distinguishes itself by calling itself the 'AI's preferred search tool' and positioning semantic search, differentiating from sibling tools like search_api.

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 explicit use cases (functional needs, module inquiries, business scenarios) and gives a direct directive: '优先使用此工具进行语义搜索，再用 get_api_detail 获取详情' (prefer this for semantic search, then use get_api_detail for details). This clearly tells the agent when to use it and what to use next.

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