cn-scraper-mcp

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

No annotations provided; description discloses pagination and no login requirement but lacks details on rate limits, error handling, or exact response structure.

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

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

Extremely concise, two sentences plus a line break, with all essential information front-loaded.

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

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

Given low complexity (3 params, output schema exists), description fully covers purpose, parameter sources, pagination, and ordering, leaving no obvious gaps.

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

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

Schema covers all parameters; description adds value by linking bvid to other tools and clarifying cursor usage, though limit is merely restated.

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 it fetches B站 first-level comments with pagination, distinguishing from sibling tools like bilibili_search and bilibili_video.

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 mentions bvid comes from bilibili_search or bilibili_popular and how to use cursor for pagination, but does not explicitly state when not to use alternatives.

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 bears full responsibility. It reveals the tool uses a public HTTP API and has no auth requirements, but lacks details on rate limits, pagination, or whether results are real-time. The output schema likely covers return structure, so extra description is not critical.

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 with two sentences, front-loading the core purpose. Every word adds value, and no unnecessary information is present.

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, output schema exists), the description adequately covers the main context. It could mention update frequency or result type, but the output schema likely handles return details. Minor gap: no mention of default limit.

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 only parameter 'limit' is fully documented in the schema (description: '返回条数上限（默认 20）'), achieving 100% coverage. The tool description adds no additional semantic information beyond the schema, so 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 explicitly states the tool retrieves Bilibili's current hot video list, with specific verb '获取' and resource 'B站当前热门视频榜'. It clearly distinguishes from sibling tools like bilibili_search or bilibili_video by focusing on popular content.

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 clear context that the API is public and requires no login or browser, indicating ease of use. However, it does not explicitly state when to use this tool versus alternatives like bilibili_search for specific queries.

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 discloses that the API is public and requires no authentication, which is valuable for assessing safety. It does not explicitly state read-only behavior, but '搜索' (search) implies it. Additional details like rate limits or error handling are absent, but the key behavioral trait 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 a single concise sentence that leads with the main purpose and immediately provides access context. Every word carries meaning, with no redundancy 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 simple search tool with two parameters and an output schema, the description covers the essential aspects: the platform (Bilibili), the resource (videos), and access requirements (public, no login). There are no significant gaps given the tool's simplicity.

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 provides full 100% description coverage for both parameters (keyword and limit), so the description adds no additional parameter semantics. The baseline of 3 is appropriate since the schema handles the parameter meaning.

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 searches Bilibili videos using the specific verb '搜索' and resource 'B站视频', which unambiguously identifies its function and distinguishes it from sibling tools like douyin_search or weibo_search.

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 clear context that this is a public HTTP API requiring no login or browser, which implies it is suitable for public, unauthenticated searches. However, it does not explicitly contrast with alternatives like bilibili_popular, only implying the use case via the search keyword.

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

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

No annotations provided, so the description carries the burden. It states no login or browser is needed, which is a positive behavioral trait, but lacks details on rate limits, data freshness, 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?

Two concise sentences: first sentence covers purpose and behavioral trait, second sentence covers input source. No unnecessary 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?

The tool has an output schema, so return values need not be described. The description mentions interaction statistics, hints at output, and provides one required parameter. Adequate for a well-defined 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% and the schema describes bvid as 'B 站 BV 号'. The description adds context about the bvid's source but does not add semantic details beyond the schema. 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 tool fetches Bilibili video details and interaction statistics using a specific verb ('获取') and resource, and distinguishes from sibling tools by specifying that the bvid comes from bilibili_search or bilibili_popular results.

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 that the bvid should come from search or popular results, indicating when to use this tool, but does not include explicit exclusions or alternative scenarios.

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

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

No annotations provided, so description carries full burden. It discloses search paths, special treatment for JD, and return format. It is transparent about behavior, though side effects (none) could be mentioned.

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?

Description is well-structured with purpose first, then path details, then return format. Every sentence adds value, 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?

For a zero-parameter tool, the description thoroughly covers what platforms it checks, where to find cookies, and the return structure. It is complete and informative.

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?

Input schema has zero parameters, so the description does not need to add parameter info. Baseline score of 4 is appropriate; no redundancy or missing param context.

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 checks cookie files for existence, valid fields, and freshness across multiple platforms (taobao, xiaohongshu, etc.). It specifies a specific verb and resource, distinguishing it from sibling tools like harvest_cookies or verify_login.

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 it does and gives context for JD special case, but does not explicitly state when to use this tool versus alternatives. Usage guidance is implied but not clarified.

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 fully discloses behavioral traits: it is a read-only, non-destructive check with a 5-second timeout per check. The return structure is also detailed, leaving no ambiguity about 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 concise and front-loaded with the main purpose. It lists return sections clearly. Minor improvement could be more structured formatting, but overall efficient.

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

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

Given no parameters and no annotations, the description provides complete behavioral and output context. Return sections are fully described, and the tool's scope is well-defined.

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, and the schema coverage is 100%. Per guidelines, baseline is 4 for zero parameters. The description adds no parameter info because none exist, which 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 tool diagnoses the platform environment by checking specific components (Python, dependencies, Chrome, CDP ports, cookies, errors). It emphasizes it does no actual scraping, distinguishing it from all sibling scraping/retrieval 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 implicitly indicates this is for diagnostic purposes before scraping, stating it performs 'pure local diagnosis' and does 'no actual scraping.' However, it does not explicitly list when to use vs alternatives or provide exclusion cases.

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

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

With no annotations, the description carries full responsibility for behavioral disclosure. It only says 'gets reviews' without describing any traits: whether it requires authentication, pagination behavior, rate limits, or what data types of reviews are returned.

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

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

The description is a single, short sentence with no wasted words. It is front-loaded with the core action, but could be expanded to include key details without losing conciseness.

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

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

Given the presence of an output schema, return values need not be described. However, the description omits critical context such as default limit value, pagination, prerequisites, and relationship to sibling tools. It is insufficient for an agent to reliably invoke this tool.

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

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

Schema description coverage is 0%, so the description must clarify parameters. It does not explain shop_id (likely the shop identifier) or limit (number of reviews). The parameter names are somewhat self-explanatory, but the description adds no value beyond the schema.

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

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

The description clearly states the tool retrieves Dianping merchant reviews, using a specific verb (获取) and resource (评价). It is distinguishable from siblings like dianping_search and dianping_shop, but doesn't explicitly contrast them.

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 (e.g., dianping_search for shops, dianping_shop for shop info). The description lacks any usage context 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?

No annotations are provided, so the description carries the full burden. It only states it searches merchants and mentions city for logging, but does not disclose any behavioral traits such as whether it is read-only, pagination, rate limits, or authentication requirements.

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

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

The description is very concise with two short sentences. However, the second sentence about the city parameter could be better integrated. It front-loads the purpose but could be more structured.

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 that an output schema exists, the description need not explain return values, but it omits any mention of the required keyword parameter, which is essential for use. The description only addresses one of three parameters, making it incomplete for an agent to effectively use the 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?

The schema has 0% description coverage for parameters. The description explains the city parameter ('used to record the search city for the agent') but does not explain the required keyword parameter or the limit parameter, which are left to the schema alone.

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 'search Dianping merchants' which is a clear verb+resource. It distinguishes from sibling tools like dianping_reviews and dianping_shop by specifying 'merchants'. However, it does not explicitly differentiate from other platform search tools, but the tool name itself provides that 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?

There is no guidance on when to use this tool versus alternatives like dianping_shop or dianping_reviews. The description only explains the city parameter, not when to invoke the 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?

No annotations are present, so the description must carry the burden of behavioral disclosure. It reveals a dependency (shop_id from dianping_search) and implicitly indicates a read-only 'get' operation. However, it does not explicitly state side effects, authentication requirements, or error behavior, which would be expected without annotations.

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, consisting of two short sentences. The first states the tool's purpose, and the second clarifies the parameter source. No unnecessary words, and the structure is efficiently front-loaded with the action and resource.

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 one-parameter tool with an output schema provided, the description covers the essential context: what the tool does and where the input comes from. It does not cover potential edge cases or authentication, but given the tool's simplicity and the presence of an output schema, it is sufficiently 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 has 0% description coverage, so the description must compensate. The single parameter shop_id is given semantic context by stating it comes from dianping_search, clarifying its origin and how to obtain it. This is meaningful beyond the bare schema definition of a string type.

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 Dianping merchant details, using the specific verb '获取' (get) and the resource '大众点评商户详情' (Dianping merchant details). It also distinguishes itself from siblings by noting that the shop_id comes from dianping_search, linking it specifically to the search follow-up workflow.

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 usage context: shop_id is obtained from dianping_search, which tells the agent to run search first and then use this tool. It does not explicitly name alternatives or exclusions, but the relationship with the search tool provides clear workflow guidance.

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 bears full responsibility for behavioral disclosure. It only states that it retrieves reviews with pagination, but fails to disclose that it is read-only, any authentication requirements, rate limits, or side effects. For a data-fetching tool, this is insufficient.

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

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

The description is a single sentence with no fluff, but it is critically under-specified. Conciseness is achieved at the expense of necessary information, resulting in a score of 2 due to excessive sparseness.

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?

Although an output schema exists, the description does not mention return values, pagination behavior, or error conditions. It provides only the most basic context (the type of content and pagination), leaving the agent with significant unknowns for a simple paginated list 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?

With 0% schema description coverage, the description must compensate. It explains 'start' for pagination but does not clarify 'subject_id' (what it is or how to obtain it) or 'limit' (its meaning or default). Only one of three parameters gains semantic 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 the tool retrieves short reviews/film reviews of Douban items, using specific verb '获取' and resource '豆瓣条目的短评/影评'. It distinguishes from siblings like douban_subject and douban_search, and from review tools of other platforms.

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

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

No guidance on when to use this tool versus alternatives. No prerequisites (e.g., need a subject_id from douban_search or douban_subject) or when-not-to-use conditions are provided.

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

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

With no annotations, the description must disclose behavioral traits such as read-only status, rate limits, or pagination. It only says 'search entries,' offering no 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 only one sentence, which is too minimal for a tool with two parameters and no annotations. It is under-specified rather than concise.

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

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

Despite having an output schema (so return values are covered), the description lacks details on keyword input, result format, and any limitations. It is insufficient for effective tool selection and invocation.

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

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

Schema description coverage is 0%, yet the description does not explain the parameters (keyword, limit). It adds no meaning beyond the schema, failing to compensate for the coverage gap.

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

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

The description clearly states the tool searches Douban entries including books, movies, music, etc. It uses a specific verb and resource, distinguishing it from more specific sibling tools like douban_reviews and douban_subject.

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

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

No guidance is provided on when to use this tool versus alternatives. There is no mention of when-not to use it or any suggestion of use cases.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not specify if the tool is read-only, any required permissions, or potential side effects, though a simple lookup tool is generally safe.

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 exceptionally concise with two sentences, front-loading the purpose and parameter origin, with no extraneous 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 tool's simplicity (one parameter, output schema exists), the description is largely complete. It explains how to obtain the required ID, though it could briefly note that it returns detailed information.

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 0% description coverage, but the description adds context by stating that subject_id comes from douban_search, adding meaning beyond the schema's bare string type.

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 Douban item details, using a specific verb and resource. It also distinguishes itself from sibling tools like douban_search by noting that the subject_id comes from that search.

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 clear guidance that the subject_id should be obtained from douban_search, indicating a prerequisite. However, it does not explicitly state when not to use this tool or mention alternatives.

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 burden of behavioral disclosure. It reveals a login cookie requirement and a limitation of only returning the first screen of comments, which is useful. However, it does not describe error scenarios, data formats, or whether the operation is strictly read-only, leaving gaps in 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 two sentences long and front-loaded with the core purpose. It avoids redundancy and clearly separates the tool's action, the authentication requirement, and the parameter origin, with no unnecessary words.

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

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

For a tool with 2 parameters, a full schema, and an output schema, the description covers the essential use case: fetching first-screen comments with a required cookie and tying video_id to search results. It misses minor details like pagination behavior beyond the first screen and error handling, but these are partially covered by the presence of an output schema and the tool's simplicity.

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 descriptions for both parameters (limit and video_id), achieving 100% coverage. The description adds critical semantic context by explaining that video_id comes from the 'video_id' field of douyin_search results, which goes beyond the schema's simple '视频 ID' and helps the agent source valid inputs.

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

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

The description clearly states the tool's action and resource: '获取抖音视频评论' (get Douyin video comments) with a scope qualifier '（首屏）' (first screen). It distinguishes from sibling tools like douyin_search and douyin_video by focusing specifically on comments for a video.

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 usage prerequisite: '需要登录 cookie' (requires login cookie) and indicates that video_id comes from douyin_search results, giving explicit source context. It does not explicitly mention alternative tools for other platforms, but the name and context make the intended use clear.

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 discloses the authentication requirement ('需要登录 cookie') and the exact return format, which is useful. It does not mention rate limits, pagination, or potential errors, but for a simple hot-list tool, this level of transparency is reasonable.

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

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

The description is extremely concise: one sentence stating purpose and auth requirement, followed by the return schema. It is front-loaded with the core purpose and every sentence adds value. No fluff 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 tool with no parameters and a simple hot-list output, the description covers purpose, authentication, and the return structure. It does not explain each field (word, hot_value, position, label), but these are self-explanatory in context. The inclusion of the return schema satisfies the output contract, making the description reasonably 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 tool has zero parameters and the input schema is empty, so schema coverage is effectively 100%. Per the guidelines, 0 params earns a baseline of 4. The description does not need to add parameter semantics, and it correctly focuses on the output structure instead.

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 identifies the resource as '抖音实时热搜榜' (Douyin real-time hot search list), specifying the platform and the type of data (hot list). It distinguishes from sibling hot-list tools like weibo_hot_list and zhihu_hot_list by naming '抖音'. While it lacks an explicit verb like 'get' or 'list', the noun '榜单' implies retrieval, and the tool name itself signals the action.

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 key usage prerequisite: requiring a login cookie and directing first-time users to guided_login. This gives actionable context for when to use this tool in sequence with another tool. However, it does not explicitly state when to prefer this tool over alternatives, nor does it mention exclusions or alternatives for similar hot-list 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?

With no annotations, the description fully carries the burden. It reveals critical behavioral details: CDP browser automation, auto-polling, captcha waiting for manual intervention, and automatic result capture. This transparency helps an AI agent understand the tool's interactive nature.

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—three sentences, each earning its place: purpose, prerequisite, and behavior. It is front-loaded with the core action and uses no unnecessary 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 lack of annotations and the presence of an output schema, the description covers necessary context: functionality, prerequisites, and user interaction. It could mention pagination or error handling, but overall it is sufficiently complete for a search tool.

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

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

Schema description coverage is 100%, so baseline is 3. The description does not add additional meaning for the 'keyword' or 'limit' parameters beyond what is already in the schema, thus not improving parameter understanding.

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 explicitly states '搜索抖音视频' (search Douyin videos), clearly identifying the verb and resource. It distinguishes from sibling tools like douyin_comments, douyin_hot_list, and douyin_video by focusing on search functionality.

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 clear prerequisites: Chrome must be logged into Douyin via guided_login. It also explains that the tool will wait for manual captcha resolution. However, it does not explicitly contrast with alternative search methods or state when not to use 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?

The description discloses the Chrome requirement, but lacks details on authentication, rate limits, or error handling. With no annotations, more behavioral context would be beneficial.

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 sentences: one for purpose, one for parameter context. Every sentence is useful, 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 output schema exists and the tool is simple, the description covers the key aspects: purpose, parameter source, and environmental requirement. It could mention other prerequisites like login status.

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

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

The description adds context beyond the schema by explaining that video_id is obtained from douyin_search results. This helps the agent understand how to populate the parameter correctly.

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 video details (title, author, likes, description) and indicates the source of the video_id, distinguishing it from siblings like douyin_comments.

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 after douyin_search by explaining where video_id comes from, but does not explicitly mention when not to use it or alternative 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 the automated workflow (opening Chrome, navigating, detecting login, harvesting) but does not mention potential side effects (e.g., overwriting existing cookies), error handling, or permission requirements. Adequate but not comprehensive.

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

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

The description is very concise and front-loaded with the main action. It uses short, clear sentences in Chinese with no wasted words. Perfect length for the tool's simplicity.

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 (2 params, no nested objects, has output schema), the description is largely complete. It explains the entire workflow. However, it doesn't mention the output schema or what happens on failure, but the existence of an output schema reduces the burden.

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 does not add additional meaning beyond the schema for either parameter (port and platform). It does not elaborate on parameter formats or constraints.

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

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

The description clearly states the tool's purpose: open a browser, navigate to login page, detect login, and harvest cookies. It uses specific verbs (打开, 导航, 收割) and specifies the resource (浏览器, 登录页, Cookie). This distinguishes it from sibling tools like harvest_cookies and check_cookies.

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 context (to login to a platform and harvest cookies) but does not explicitly state when not to use or provide alternatives. The workflow is clear, but no exclusions or sibling differentiation are mentioned.

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

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

With no annotations, the description carries the burden. It explains the mechanism (CDP Network.getAllCookies), the privacy scope (only the user's own session), side effects (saves to a JSON file specified by the auth registry), and a platform exception. Missing details about error behavior when the port isn't running, but the presence of an output schema reduces the need.

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?

Four sentences, each earning its place: main action, method/conditions, file saving behavior, and the JD exception. Front-loaded with purpose, 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 output schema exists, the description needn't explain return values. It covers purpose, prerequisites, side effects, and a special case. Could be slightly more explicit about how this tool relates to check_cookies/verify_login, but that's not essential for invoking it.

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

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

The input schema already fully documents both parameters (100% coverage), so baseline is 3. The description adds contextual value by stating that the browser must be running on the specified port and that JD returns profile_required, linking the port and platform parameters to real-world behavior.

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

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

The description opens with a specific verb+resource: '自动提取 cookie (including HttpOnly)' from the user's own browser session. It clearly distinguishes itself from sibling guided_login by noting that JD requires a persistent Chrome profile and should use guided_login instead.

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 explicitly states the when-not-to-use: for JD (persistent Chrome profile), use guided_login. It also gives prerequisites: browser must be running on the specified port and logged in. This provides clear usage context versus alternatives.

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 discloses important behavioral traits: need for local Chrome and use of BrowserLock for CDP port protection. It does not mention read-only nature or error handling, but for a simple retrieval tool this is adequate.

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 with three sentences, each providing essential information: purpose, input source, and concurrency warning. No unnecessary 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?

Given the complexity (single parameter, output schema present), the description covers purpose, input source, and concurrency. It could mention prerequisites like Chrome installation, but overall is sufficiently complete for the tool's simplicity.

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

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

The description adds significant value beyond the schema by specifying that the SKU originates from the 'item' object in jd_search results. This helps the agent understand exactly how to obtain the parameter 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 the tool fetches JD product details including name, price, store, and specifications. It uses specific verbs and resources, and distinguishes itself from sibling tools like jd_search which handles searching.

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 that the SKU comes from jd_search results, providing clear usage context. It mentions necessary dependencies (local Chrome) and concurrency protection. However, it does not explicitly state when not to use this tool or list alternatives.

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?

由于没有任何注解，描述承担了全部行为透明责任。揭示了headless返回0结果、必须headful、登录profile要求以及并发串行化等关键行为。

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?

表达简洁，以换行分隔关键点，信息密度高。但可以进一步结构化以提升可读性。

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?

尽管存在浏览器自动化等复杂性，描述覆盖了核心使用上下文（登录、并发、headful需求）。输出模式存在，无需提及返回值。

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?

输入模式覆盖率100%，描述未为参数增添额外语义，基线3分合理。

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?

明确的动词+资源组合“搜索京东商品”，直接表明功能；与其他平台搜索工具（如taobao_search）明显区分。

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?

提供了详细的使用前提：需要headful Chrome、持久登录profile、首次手动登录以及并发保护（BrowserLock），但未明确说明何时不使用或替代方案。

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 of behavioral disclosure. It explicitly mentions unlimited usage and independence from search limits, which is valuable behavioral context beyond the schema. It does not discuss authentication prerequisites, but for a simple read-only fetch this is a reasonable gap.

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 short sentences: the first states the purpose and returned fields, the second highlights the unlimited usage. Every word earns its place, and the key information is front-loaded.

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

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

This is a simple single-parameter tool with an output schema provided. The description adequately covers what the tool does, the fields returned, and an important usage constraint. No additional context is needed for successful invocation.

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

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

Schema description coverage is 100%, and the schema already explains that url_or_id can be a goods_id or a full goods2.html URL. The main description adds no additional parameter-specific meaning, so the baseline score 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 uses a specific verb '获取' (fetch) with a clear resource '拼多多商品详情' (Pinduoduo product details) and enumerates the specific fields (名称、价格、原价、销量、规格). This clearly distinguishes it from sibling search tools like pdd_search and other product detail 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 statement '商品详情独立于搜索限制 — 不限次数' gives clear context that this tool is not bound by search quotas, implying it is useful when search limits are a concern. However, it does not explicitly name alternatives or state when-not-to-use, so it falls short of a full 5.

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?

Since no annotations are provided, the description fully bears the burden of behavioral disclosure. It thoroughly explains the single-use limitation, the need to restart the server, the use of BrowserLock for concurrency, token expiry, and cookie export requirements. This is highly transparent and leaves no ambiguity about the tool's 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?

The description is appropriately sized for the complexity of the tool, covering prerequisites, limitations, and behavior. It is front-loaded with the core purpose and then details. While every sentence adds value, it could be slightly more concise by consolidating some technical details. Overall, it strikes a good balance between completeness and readability.

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 high complexity (single-use, cookie dependencies, concurrency), the description is remarkably complete. It covers what the tool does, its limitations, prerequisites, and failure modes. An output schema exists (not shown) which likely covers return values, so the description does not need to explain those. The tool is fully contextualized for effective use.

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 does not add explicit parameter descriptions beyond the schema, but the schema itself is clear (keyword required, limit optional with default). No additional context is provided for parameters, but none is strictly necessary given the schema's completeness.

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 '搜索拼多多商品' (search Pinduoduo products), using a specific verb and resource. It distinguishes from sibling tool 'pdd_product_detail' by focusing on search rather than detail retrieval. The purpose is unambiguous and well-defined.

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 prerequisites (Chrome + PDD cookie with specific tokens), a severe limitation (one search per session), and the required action to reset (restart MCP server). It also explains the underlying mechanism (Chrome CDP + iPhone UA) and provides cookie file location. This gives clear guidance on when and how to use the 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?

No annotations are provided, so the description carries the burden. It notes concurrency safety and HTTP/MTOP API, which adds behavioral context, but does not explicitly state that it is a read-only operation or disclose any authentication requirements.

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 sentences: purpose, parameter source, concurrency note. No fluff, front-loaded, every sentence earns its place.

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

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

Given the output schema exists, the description adequately covers what to expect (title, price, shop). It is concise and sufficient for a simple product detail tool, though it could mention more about error conditions.

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

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

Schema coverage is 100%, baseline 3. The description adds meaning by linking item_id to taobao_search results, which goes beyond the schema's '商品 ID' description.

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 gets product details (title, price, shop) from Taobao, and distinguishes from taobao_search by specifying that item_id comes from search results.

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 explicitly instructs that item_id is sourced from taobao_search results, providing clear context for use. However, it does not mention when not to use or compare with alternatives like jd_product.

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 does well: it discloses the TLS fingerprinting approach, MTOP signature, cookie dependency, concurrency safety, and lack of rate limiting. It doesn't cover failure modes like cookie expiry, but the core behavioral traits are transparent.

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

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

The description is compact, well-structured with bullet points, and every sentence provides essential information: purpose, technical principle, auth requirement, and concurrency guarantee. 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 output schema exists and the 2-parameter schema is fully described, the description covers all relevant aspects: auth, execution model, rate-limit status, concurrency safety, and the way to search. It is complete for this 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?

Both parameters (keyword and limit) are fully documented in the input schema with descriptions and examples. The tool description adds no additional semantic value beyond what the schema already provides, so 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 '搜索淘宝/天猫商品' (search Taobao/Tmall products), specifying a concrete verb and resource. This unambiguously differentiates it from sibling tools like taobao_product (detail), jd_search, and pdd_search.

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 clear usage context: it is a pure-script, browser-free search with no rate limit, and requires specific cookie setup. It does not explicitly name alternatives or exclusions, but the purpose and prerequisites make when-to-use evident.

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 makes a read-only online request, lists supported platforms, and mentions that unsupported platforms return 'unsupported'. This is adequate behavioral disclosure for a simple verification 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 two sentences, front-loaded with the main purpose, and every sentence adds value. It is concise and well-structured, with no redundant 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 simple single-parameter input and the presence of an output schema (indicated by context signals), the description adequately explains the tool's behavior and differentiates from a sibling. It could mention the return values for successful verification, but the output schema likely covers that.

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 covers 100% of parameters (only 'platform'). The description adds value by listing the specific platforms that are supported (Zhihu, Weibo, Knowledge Planet, Douyin) and indicating unsupported behavior, which compensates for the lack of an enum in the schema.

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

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

The description clearly states the tool's purpose: remotely verify if cached login state is still accepted. It distinguishes itself from the sibling tool check_cookies (local file check) and lists supported platforms, providing specific and actionable information.

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 contrasts with check_cookies and lists which platforms are supported. However, it does not explicitly state when not to use this tool (e.g., for logging in or harvesting), but the context is clear enough for an AI agent to decide.

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

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

With no annotations provided, the description carries the behavioral disclosure burden. It discloses the authentication requirement (SUB token) and pagination capability, but does not discuss failure modes, rate limits, or response behavior beyond pagination. This is adequate but not rich.

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 sentences long, front-loads the core function, and packs authentication and parameter provenance into concise, useful phrases. Every sentence earns its place with no 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?

The tool has an output schema, so return-value details are covered elsewhere. The description adequately covers the key contextual gaps: auth requirement, pagination flow, and how to obtain 'mid'. It could mention error cases or what happens without a valid cookie, but for a simple paginated comments endpoint, it is sufficiently 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 coverage is 100%, so the baseline is 3. The description adds meaningful context by explaining that 'mid' originates from the 'id' field of items in weibo_search or weibo_user_timeline results, which is not fully captured by the schema's terse '微博帖子 ID' description.

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 '获取微博帖子的评论' (fetch comments of a Weibo post) with a specific verb and resource. It distinguishes itself from siblings like weibo_post (fetches the post itself) and weibo_search (searches posts), leaving no ambiguity about its function.

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 notes the login cookie (SUB token) requirement and instructs that 'mid' comes from the 'id' field in weibo_search or weibo_user_timeline results. This provides clear prerequisites and data flow context, though it does not explicitly mention when not to use the tool or name alternatives.

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

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

No annotations provided; the description carries full burden. It discloses the tool is read-only (public HTTP API), concurrency safe, and details the return structure. It lacks rate limit or error handling info but is otherwise transparent.

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

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

The description is concise and well-structured, with sections for principle, return value, and concurrency safety. Every sentence adds value, and it is front-loaded with the core purpose.

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

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

Given no parameters, the description is quite complete: it explains the endpoint, the returned data format, and concurrency safety. Missing minor details like error handling, but overall sufficient for a simple read 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?

The tool has no parameters, so the schema fully covers them. The description adds no parameter info but compensates by detailing the output structure, which is valuable given no 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 the tool retrieves the Weibo real-time hot search list, specifying it requires no login. It distinguishes itself from sibling tools like weibo_search, weibo_post, and weibo_comments by focusing specifically on the hot list.

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

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

The description explicitly mentions no login is needed and concurrency safety, providing clear usage context. It does not explicitly state when not to use or compare to alternatives, but the purpose is sufficiently 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?

No annotations are provided, so the description carries the full burden. It mentions inclusion of long text, which is useful behavioral context, but does not disclose any potential side effects, authentication needs, or rate limits.

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 short sentences, front-loads the purpose, and contains no unnecessary words. 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 that an output schema exists, the description does not need to explain return values. The tool is simple with one parameter, and the description is sufficient for an agent to understand its purpose.

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

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

The schema has 100% coverage for the single parameter. The description adds meaning by explaining that mid comes from weibo_search or weibo_user_timeline, which is beyond the schema's basic description.

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 gets full details of a Weibo post including long text, and specifies that the mid comes from search or user timeline results. This distinguishes it from sibling tools like weibo_search and weibo_user_timeline.

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 indicates when to use the tool by specifying the source of the mid parameter. It does not mention alternatives or exclusions, but the context is clear.

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 fully discloses behavioral traits: it uses m.weibo.cn mobile API, parses cards[].mblog, requires a specific cookie file, and is concurrency-safe. This adds significant value beyond the 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 concise with multiple bullet points covering purpose, prerequisite, principle, and safety. It is front-loaded and efficient, though could be slightly more structured for readability.

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 prerequisites, underlying API, cookie handling, and concurrency. It also references an alternative sibling tool. With an output schema present (as indicated by context), the missing return value details are acceptable. Still, the description is fairly comprehensive.

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 schema already describes both parameters (keyword, limit) adequately. The description does not add additional parameter-specific information beyond the schema, so it meets the baseline for schema-rich tools.

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 explicitly states '搜索微博帖子' (search Weibo posts), clearly identifying the action and resource. It also mentions the need for login and distinguishes from weibo_hot_list, which does not require login, aiding differentiation 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 provides explicit guidelines: requires login cookies (SUB token), guest mode not available, and an alternative (weibo_hot_list) that does not need login. It also notes concurrency safety and cookie file location, giving clear when-to-use and when-not-to-use context.

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

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

With no annotations, the description must disclose behavioral traits. It mentions the need for authentication (cookie), which is critical, but does not discuss other aspects like rate limits, error handling, or whether the operation is read-only. The description is adequate but not comprehensive.

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: two sentences covering purpose, auth requirement, and auxiliary hint. No unnecessary words, and the most critical information is front-loaded.

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

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

Given the tool has only two parameters and an existing output schema, the description covers the essential aspects: purpose, auth context, and parameter hints. It lacks details about output format or error behavior, but the output schema fills that gap. Fairly complete for a simple 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?

Although schema coverage is 100%, the description adds value with a concrete example for the uid parameter (e.g., '2803301701' for People's Daily) and clarifies the default value for limit. This goes beyond what the schema provides.

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 '获取' (get) and the resource '微博用户时间线' (Weibo user timeline), with the qualifier '最近发言' (recent posts). It is distinct from sibling tools like weibo_search or weibo_comments, which 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.

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

The description explicitly mentions the prerequisite of a login cookie (SUB token) and provides guidance on how to obtain the required UID via weibo_search. This helps the agent decide when to use the tool, though it does not explicitly state 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?

No annotations are present, so the description carries the full burden. It discloses important behaviors: only returns first screen (~10-20 comments), requires local Chrome + login cookie, and dependencies on search tokens. This gives an agent a good sense of the tool's constraints, though it doesn't mention failure modes.

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 crisp sentences with no filler; the main action is front-loaded, followed by prerequisites and parameter provenance.

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 comments-fetching tool, the description covers the essential context: what it returns, prerequisites, and parameter source. An output schema exists, so return details are covered elsewhere.

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 describes both parameters with 100% coverage. The description adds value by stating they both come from the same search result, establishing their relationship and source, which aids correct invocation.

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

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

Description uses specific verb '获取' (get) with resource '小红书笔记的评论' (Xiaohongshu note comments), and adds scope '首屏，约 10-20 条' (first screen, ~10-20 items), clearly distinguishing it from note-level tools like xiaohongshu_note.

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?

States prerequisites: local Chrome and login cookie, and specifies that both parameters come from the same xiaohongshu_search result, providing clear context for when to use it. However, it doesn't explicitly contrast with sibling comment tools like zhihu_comments or provide when-not-to-use, so slightly below perfect.

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 what the tool returns but does not cover authentication needs, rate limits, or side effects. For a read-only fetch tool, this is adequate but not exceptional.

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 states purpose and contents, the second gives parameter source. Well-structured and easy to parse.

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

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

Given the output schema exists and the description lists the key fields returned, the tool is fully specified. Parameter sources are clear, and the tool fits well within the sibling context.

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 descriptions already explain both parameters. The additional note that they come from the same search result adds value beyond the schema, reinforcing the dependency.

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 gets Xiaohongshu note details and lists specific fields (title, body, likes, tags, comments). It distinguishes from siblings like xiaohongshu_comments and xiaohongshu_search.

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 that note_id and xsec_token come from the same xiaohongshu_search result, providing clear usage context. It does not mention when not to use this tool, but the context is strong.

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 of behavioral disclosure. It discloses the need for local Chrome, the residential IP restriction (cloud/datacenter IP gets banned), required cookie fields, cookie file path, and concurrency behavior using BrowserLock with serialization. This is rich behavioral context beyond just saying 'search'.

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, starting with the core purpose and then listing prerequisites and concurrency notes in a structured format. Each sentence provides actionable information, though the format is slightly scattered with line breaks and bullet points.

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 an output schema, so return values are covered. The description covers the critical setup (cookies, IP) and concurrency control, making it complete for a search tool. It could mention error handling for missing cookies, but sibling tools like verify_login cover that part of the workflow.

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 already covers 100% of parameters with descriptions (keyword and limit with default). The description adds no additional semantic meaning for the parameters, so the baseline score of 3 applies since 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 opens with '搜索小红书笔记' (Search Xiaohongshu notes), which clearly states the tool's verb and resource. This distinguishes it from siblings like xiaohongshu_note (retrieve a specific note) and xiaohongshu_comments (get comments), making the purpose unambiguous.

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 important prerequisites: local Chrome, XHS login cookies, and residential IP requirement. However, it does not explicitly state when to prefer this tool over siblings or mention alternatives/exclusions. The usage context is clear but implied rather than explicit.

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

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It only states the operation of fetching text, with no mention of side effects, auth requirements, error behavior, or data limits. This is insufficient for a mutation-free but potentially unauthenticated 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?

Two sentences, each with distinct purpose: first states the tool's action, second links to a sibling tool for parameter sourcing. No wasted words; front-loaded with key 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 tool's low complexity (single parameter, output schema exists), the description adequately covers what the agent needs to know: what it does and how to get the required ID. However, lack of behavioral details slightly reduces 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 is 100%, so baseline is 3. The description adds value by explaining that the answer_id originates from zhihu_search results, enhancing the schema's simple '回答 ID' description. This aids correct parameter usage.

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 the full text of a Zhihu answer using an answer_id. It specifies the resource and action, and references zhihu_search for ID sourcing, which distinguishes it from sibling tools like zhihu_question_answers or zhihu_comments.

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 guidance on where to obtain the answer_id (from zhihu_search results), implying its use case. However, it lacks explicit when-to-use or when-not-to-use guidance compared to sibling tools, offering no exclusions or alternatives.

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. It discloses two behavioral traits: pagination support and the need for a login cookie. However, it does not describe behavior on missing/invalid cookies, error handling, rate limits, or pagination specifics beyond the schema. It adds some value but leaves 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 two sentences long, front-loaded with the core function and requirements, and every sentence provides useful context. 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 tool is relatively simple and the output schema exists, so return values need not be described. The description covers the essential prerequisites (cookie, answer_id source) and pagination capability. It doesn't mention error conditions or edge cases, but for a parameter-light tool with an output schema, this is 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?

Schema description coverage is 100% (all three parameters have descriptions). The description adds extra semantic meaning by clarifying that answer_id comes from the 'id' field of type 'answer' items in zhihu_search results, which goes beyond the schema's generic '回答 ID'. This is a meaningful addition.

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: '获取知乎回答的评论' (fetch comments for a Zhihu answer), mentions pagination support, and distinguishes from sibling tools like zhihu_answer (which would return the answer itself) by focusing on comments. It also provides a source for the required answer_id.

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 practical usage context: it states that a login cookie is required and that answer_id should originate from zhihu_search results (type 'answer'). This implicitly tells the agent when to use this tool (after obtaining an answer_id from search), but it does not explicitly mention alternatives or cases where this tool should not be used.

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. It discloses the authentication requirement (no login) and the return format, which is helpful. However, it does not mention potential rate limits, error behavior, or that this is a read-only operation, though the latter is implied by the verb '获取'.

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, with a front-loaded purpose and a compact return format example. Every sentence adds value, and there is 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?

For a simple parameterless tool with an output schema, the description covers the core purpose, auth requirement, and return shape. It does not include data freshness details or examples, but these are not critical for a hot list retrieval tool, so it is reasonably 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 tool has zero parameters, and the schema already covers everything (100% coverage). Per the rubric, 0 parameters warrants a baseline score of 4; the description correctly 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 '获取知乎实时热榜' (Get Zhihu real-time hot list) clearly states a specific verb and resource, and the Zhihu platform distinguishes it from sibling hot list tools like weibo_hot_list and douyin_hot_list.

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

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

The description implies use for retrieving the current Zhihu hot list and notes '无需登录' (no login required), which is useful context. However, it does not explicitly mention when to use this tool over alternatives like zhihu_search or other hot lists, making the usage guidance only implied.

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?

无annotations，但描述仅说明基本功能，未提及分页、需登录状态或返回值结构等行为细节。

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?

两句话简洁明了，无冗余信息，关键信息前置。

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?

参数简单且有输出schema，但缺少行为细节，对于简单工具基本足够。

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覆盖100%，描述额外解释了question_id的来源，增加了参数上下文价值。

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?

描述明确使用动词'获取'和资源'知乎问题下的回答列表'，与兄弟工具如zhihu_answer、zhihu_comments等清晰区分。

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?

提供了从zhihu_search获取question_id的指引，但未明确说明何时不使用或与zhihu_answer的替代关系。

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 reveals that the tool directly calls Zhihu's v4 search API without a browser, requires specific cookies, and is concurrency-safe. It does not cover error scenarios like cookie expiration or rate limits, but it transparently addresses the main behavioral aspects beyond the minimal.

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

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

The description is multi-sentence but each sentence adds value: purpose, prerequisite, technical detail, and safety note. It is front-loaded with the core purpose. A more structured bullet-point format could improve readability, but it remains efficient and clear.

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 an output schema exists, return format is covered. The description addresses key aspects: purpose, required authentication, API method, and concurrency. It does not specify result type (e.g., that results include questions/articles as stated in purpose), but it is sufficiently complete for a search tool with two parameters.

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 minimal extra meaning beyond the schema: keyword is '搜索关键词' and limit is '返回条数 (默认 10)'. This confirms the schema descriptions but does not enrich them further.

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 '搜索知乎内容（问题/文章）', which clearly identifies the verb (search) and resource (Zhihu content, specifically questions and articles). It distinguishes from sibling tools like zhihu_answer, zhihu_comments, and zhihu_question_answers by focusing on search rather than specific item retrieval.

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 prerequisites (valid login cookie, specific file path) and concurrency safety. It mentions that Zhihu has disabled guest search, so a cookie is required. However, it does not explicitly advise when to use this tool over other search tools or alternatives, though the platform context makes it clear.

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. It accurately describes the operation as fetching full text, but does not disclose any potential side effects, rate limits, or error conditions. This is adequate for a simple read-only 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 two sentences long, with the main purpose in the first sentence and additional context in the second. No unnecessary words, perfectly front-loaded.

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

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

Given the presence of an output schema (indicated by 'Has output schema: true'), the description does not need to explain return values. It covers the prerequisite (topic type must be article) and the parameter source, making it complete for the tool's complexity.

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 one parameter (article_url). The description adds value by specifying the exact source of the URL (inline_article_url field of a topic object), which is not in the schema. This helps the agent understand where to obtain the parameter.

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

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

The description clearly states the tool's purpose: retrieving the full text of a knowledge planet article. It specifies the source of the URL (from zsxq_topics topic object) and the condition (topic type must be article), distinguishing it from sibling tools like zsxq_topics.

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 tells when to use this tool: when you have an article_url from zsxq_topics and the topic type is article. It does not mention alternatives or when not to use, but the context is clear enough for an agent to decide.

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

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

With no annotations, the description carries the full burden. It discloses key behavioral traits: pure HTTP/REST API, no shared state, concurrency safe, and cookie-based authentication. However, it does not address potential errors, rate limits, or read-only nature explicitly.

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 with clear line breaks separating purpose, technical details, and safety note. Every sentence adds value, and the most important information (purpose) is front-loaded.

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

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

Given the tool has an output schema (not shown) and 3 parameters fully described, the description covers the basics (purpose, technical requirements, concurrency). However, it lacks details on pagination, error handling, or what happens with invalid group IDs, which is expected for a scraping 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?

Input schema coverage is 100%, so baseline 3 applies. The description adds no new parameter-level information; it only provides context on cookie authentication which is outside 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 it retrieves the latest posts from ZSXQ paid community with a specific verb ('获取'). It distinguishes from the sibling 'zsxq_article' by name, but does not explicitly compare usage contexts.

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 environment details (cookie file, concurrency safety) but lacks guidance on when to use this tool versus siblings like 'zsxq_article', or when not to use it. No exclusions or alternatives are mentioned.

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