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

No annotations are present, so the description carries the full behavioral disclosure burden. It does disclose a key behavioral trait: the operation is asynchronous and results are automatically polled. However, it does not cover read-only safety, authentication needs, failure modes, or what the initial call returns, leaving some behavior unexplained.

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

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

The description is one compact, front-loaded sentence: the action and target come first, followed by the important async polling caveat. It contains no filler, repetition, or unnecessary schema duplication.

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

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

With no output schema and no annotations, the description is only minimally complete: it tells the agent what to call and that polling is automatic, while the schema handles parameters. It leaves gaps around return shape, error behavior, and the exact async workflow, which would matter for reliable agent 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%, so all four parameters (url, offset, dataNum, sortType) already have meaningful documentation including defaults and an enum. The description adds only general context and no parameter-level detail beyond what the schema provides, so the baseline score of 3 is appropriate.

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

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

The description states a specific action and resource: fetch Bilibili video comments, and adds the notable async auto-polling behavior. It is clear and unique among the sibling tools, though it does not explicitly differentiate itself from tools like bilibili-video-downloader or bilibili-search-download.

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

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

The description gives a clear target use case—retrieving comments for a Bilibili video—and the async polling detail sets expectations. However, it does not explicitly state when not to use it, mention alternatives, or provide exclusion criteria against the many sibling Bilibili and comment-related 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 carries the behavioral burden. It states the core behavior—keyword-based account search—but does not disclose result shape, match semantics, pagination behavior, or any limits. For a read-only search tool this is a moderate gap rather than a serious safety issue.

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 that front-loads the resource and action. There is slight redundancy between '账号搜索' and '搜索B站UP主', but overall it is efficient and free of 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 fully documented parameters, the description is minimally viable. However, without an output schema it does not hint at what the response contains, and it lacks usage differentiation from sibling Bilibili search tools.

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% for all three parameters, so the schema already documents keyword, page, and order. The description adds no parameter-specific meaning beyond what the schema provides, matching the baseline for full schema coverage.

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 a clear verb ('搜索') and a specific resource ('B站UP主/账号'), making the tool's purpose immediately understandable. The account scope also distinguishes it from sibling tools like bilibili-keywords-search, which by name targets general keyword content 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 implies use when searching for Bilibili accounts/UP主 by keyword, but it gives no explicit when-to-use guidance or contrast against related siblings such as bilibili-keywords-search or bilibili-portfolio-search. No exclusions or alternative routing 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?

There are no annotations, so the description must carry the burden of explaining behavior. It only says it searches Bilibili videos; it does not disclose pagination behavior, sort/publishTime semantics, result format, rate limits, or whether it is a read-only operation. This is minimal for a search tool with no annotation support.

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 short and front-loaded, containing only one sentence. It is efficient, though slightly redundant ('内容搜索' followed by '搜索B站视频'), and could have used the space to mention key parameters or alternatives.

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

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

With four parameters, no output schema, no annotations, and a large sibling set containing multiple Bilibili search tools, the description is under-specified. It does not explain how sortType/publishTime affect results, what the return data looks like, or how this tool differs from bilibili-search-download and bilibili-keywords-accounts.

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 basic meanings of keyword, page, sortType, and publishTime are already documented. The description adds no value beyond confirming keyword-based search and does not explain sortType choices or publishTime formats, but the high schema coverage keeps this at baseline.

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

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

The description states a specific action ('搜索') and resource ('B站视频'), and clarifies it is keyword-driven. It does not explicitly contrast itself with sibling tools like bilibili-search-download or bilibili-keywords-accounts, so it distinguishes the core operation but not the full sibling set.

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

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

The usage context is implied: an agent can infer this tool is for searching Bilibili videos by keyword. However, no explicit guidance is given for when to prefer this over bilibili-search-download, bilibili-keywords-accounts, or bilibili-portfolio-search, and no alternatives or exclusion conditions 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?

没有提供注解，描述承担了完全的行为披露责任。它仅说明'查询'，未提及分页、返回的元数据类型、认证要求、速率限制或可能的失败模式。对于只读操作，除'查询'外没有更丰富的上下文。

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?

描述是单句话，没有冗余或填充内容。核心功能被直接且前置地传达。每一部分都有价值，没有浪费的上下文。

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?

对于只有1个必填参数且无输出模式的简单工具，描述提供了最低限度的可操作性，说明了会返回作品列表，但未说明列表项的结构。由于复杂度低，这个缺口可以容忍，但若补充输出字段信息会更好。

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?

输入模式已完全描述了uid参数（'B站用户UID'），覆盖率为100%。描述没有为uid增加额外语义，如格式、获取方式或约束。根据规则，当模式覆盖率高且描述未添加超越模式的信息时，基线得分为3是合适的。

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'B站用户作品列表查询'明确了一个特定的操作（查询）和资源（B站用户的作品列表）。'用户'和'作品列表'的组合使其与兄弟工具如bilibili-search-download和bilibili-comment清晰区分。尽管简短，但它唯一地定义了工具的功能。

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?

描述没有提供任何关于何时使用此工具而非替代方案的指导，例如与bilibili-search-download或bilibili-video-downloader的区别。没有排除条件、前提条件或选择偏好。Agent无法根据描述决定在哪些场景下优先使用此工具。

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 of disclosing behavior. It does disclose the core behavior: input keyword, search all Bilibili videos, sort by views/likes/time, and automatically batch-retrieve HD download links. However, it does not clarify whether this returns link lists only, whether actual downloads occur, or any limitations or side effects, leaving room for ambiguity.

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

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

The description is compact and front-loaded with the tool's core purpose, followed by use-case guidance and trigger words. The trigger word list is somewhat repetitive but serves a clear intent-detection purpose, so the length is justified.

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 explains enough about expected behavior and return intent: it will search videos and get HD download links. Given the moderate complexity of five simple parameters and no output schema, the description is reasonably complete, though it could add more detail about pagination behavior or what the downloaded-link output looks like.

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, but the description adds meaning by explaining that the order parameter supports sorting by play count, likes, and time, which the schema's 'day-如 play' placeholder does not fully convey. It also reinforces that keyword is the primary required input, adding slight 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 identifies a specific action and resource: searching Bilibili's full site by keyword and batch-retrieving HD download links. It is distinct from video-downloader siblings by emphasizing keyword-based search and batch behavior, though it does not explicitly name an alternative or contrast itself with bilibili-video-downloader.

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

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

The description explicitly states when to use the tool: when the user needs to search Bilibili videos, download Bilibili content, or collect Bilibili material, and it provides trigger words for intent detection. It does not describe exclusions or when a different sibling tool would be more appropriate, so it falls one point short of full 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?

With no annotations, the description carries the full burden and does disclose the key behavior: download and return a video address. It does not mention limitations such as public availability, authentication, membership-only videos, or the exact form of the returned address, so disclosure is only minimally 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?

A single front-loaded sentence with no filler. It states action, input, and output in compact Chinese, so every part 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?

For a one-parameter, no-output-schema downloader, the description is nearly sufficient: it names input and return value. It still lacks a note about accepted URL variants or error conditions, but these are minor for this 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?

Schema description coverage is 100 percent and the schema already documents the url parameter with an example. The description only restates the idea of a video link, adding no new semantic detail 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 states a specific verb and resource: it downloads Bilibili videos from a video link and returns the video address. This clearly distinguishes it from platform-specific sibling downloaders such as youtube-video-downloader or tiktok-video-downloader.

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 tool's purpose implies use when the user provides a direct Bilibili video URL, and the sibling names make platform selection easy. However, it never explicitly states when to prefer this over related Bilibili tools like bilibili-search-download or what URL forms are unsupported.

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 carry behavioral disclosure; it does indicate a query/search operation over a 30-day window across platforms. However, it does not describe return shape, result ordering, viral-content filtering semantics, pagination, or any limitations, so behavioral transparency is only partial.

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?

A single front-loaded sentence with no filler; every phrase contributes either scope or 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?

Adequate for a straightforward search tool: the required parameter is clear and all parameters have schema descriptions. However, with no output schema and no annotations, the description does not explain response format, supported platform codes, or behavior when start/end dates are omitted, leaving a moderate gap.

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 the baseline is 3. The description adds value by signaling the default temporal window (last 30 days) and the viral-content intent, which are not fully captured in the individual parameter descriptions.

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

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

The description names a specific action (search/query), a resource (multi-platform content), and an explicit temporal scope (last 30 days). The '跨平台' phrase clearly separates it from platform-specific siblings like douyin-search or 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 states the intended context: cross-platform, keyword-based, last-30-days viral-content search. It does not explicitly list when-not cases or alternatives, but the multi-platform and timeframe conditions give an agent enough signal to select this over single-platform siblings.

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

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

With no annotations provided, the description carries the burden and does disclose meaningful behavior: a daily 15:00 update lag, sorting by likes, and a no-data-date confirmation requirement. It does not mention auth, rate limits, or output details, but the disclosed behaviors are substantive for invocation decisions.

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 dense sentence that front-loads the tool's identity ('文旅B站信息源查询'), then state scope, sort order, update timing, and a caveat. Every clause 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?

For a low-complexity, three-optional-parameter query tool, the description covers purpose, data freshness, sorting, and an important edge case about missing data. The only gap is that no output schema or return-shape description is provided, which is a minor omission for a feed-style 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 the schema already documents date, count, and keyword semantics. The description's mention of '按关键词与日期' adds nothing material beyond the schema, making the baseline 3 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 states a specific action ('获取') on a specific resource ('文旅类B站热门视频') and adds the sorting criterion (点赞量排序). It clearly distinguishes itself from sibling cultural-tourism feeds for other platforms by naming B站, and from generic Bilibili tools by the 文旅 qualifier.

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 gives useful operational context: data updates daily at 15:00 for the previous day, and dates without data must be confirmed before querying. It does not explicitly compare to sibling alternatives like bilibili-keywords-search or cultural-tourism-douyin-feed, so it stops short of full alternative-routing 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?

With no annotations provided, the description carries the disclosure burden. It discloses useful behavior: results are sorted by likes, data has a daily 15:00 update lag for the previous day, and missing data requires confirmation. It does not detail return fields or side effects, but "查询" and the listed behavior make the read-only nature reasonably clear.

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 with the core purpose front-loaded and the update/missing-data caveat kept to one compact clause. Every part 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?

For a read-oriented feed query with three optional parameters and no output schema, the description supplies key context: what is returned ("热门作品"), ordering ("点赞量排序"), freshness ("每日15:00更新前一天"), and a missing-data caution. Its only notable gap is not clarifying what the "确认后再查" confirmation process entails.

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 echoes keyword and date concepts but adds no meaning beyond the schema, and it does not explain the count parameter. This is acceptable because the schema already documents all three parameters with defaults and limits.

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

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

The description names a specific resource ("文旅抖音信息源") and a concrete action ("获取文旅类抖音热门作品"), and adds a sorting behavior ("点赞量排序"). Even without naming siblings, the 文旅/Douyin scope clearly separates it from other platform feeds and generic Douyin hot-topic 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?

It establishes a clear usage context: query by keyword and date for cultural-tourism Douyin hot content. It also gives operational timing ("数据每日15:00更新前一天") and a caution about missing dates ("无数据日期必须确认后再查"), though it does not explicitly enumerate sibling alternatives or exclusions.

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

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

With no annotations, the description carries the full behavioral burden and discloses meaningful traits: daily update timing, previous-day data coverage, no-data-date confirmation, and read-count ordering. For a non-destructive feed query this is strong context, though auth/rate-limit details are not 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?

Two tightly packed sentences: purpose and sorting in the first, data freshness and an operational caveat in the second. No filler; 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?

For a simple query tool with 3 optional, fully documented parameters and no output schema, the description covers the return type (hot articles sorted by read count), data freshness, and the no-data behavior. The lack of an explicit output shape is a minor gap but does not block tool selection or 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%, so the baseline is 3. The description's 按关键词与日期 adds little beyond the schema, while the update-timing sentence adds minor contextual meaning to the date 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?

States a specific verb and resource: 查询/获取文旅类公众号热门文章, sorted by 阅读量. The platform (公众号/WeChat) and topic (文旅) clearly distinguish it from sibling feeds such as cultural-tourism-bilibili-feed or wechat-10w-hot.

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

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

Provides usage context: query by keyword and date, data refreshes daily at 15:00 for the previous day, and dates with no data require confirmation. It does not explicitly state when to choose this tool over the many sibling wechat or cultural-tourism feeds, so selection is left to inference.

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 meaningful behavioral traits: results are sorted by likes, data is refreshed daily at 15:00 for the prior day, and there is a no-data caveat requiring confirmation before querying. It does not describe the return format or what happens on an empty date, but the key operational behaviors are covered.

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

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

A single compact sentence that leads with the tool's purpose, then the data freshness schedule, then the confirmation caveat. Every clause adds value and there is no redundant filler, making it easy to scan.

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 query tool with three optional parameters and no output schema, the description covers what it does, how data is updated, and an important availability caveat. The 'must confirm' instruction is slightly ambiguous regarding how to confirm and what happens on missing dates, and no output shape is specified, but the core information needed for invocation is present.

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 3 applies. The description adds '按关键词与日期' and '点赞量排序', but that is largely restating schema intent or describing result ordering rather than adding new parameter semantics. It does not substantially compensate beyond what the schema already documents.

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

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

The description states a specific verb ('获取', retrieve) and resource ('文旅类小红书热门笔记', cultural-tourism Xiaohongshu popular notes), with explicit criteria: keyword, date, and like-count ordering. The '文旅' prefix clearly distinguishes it from sibling Xiaohongshu feeds such as xiaohongshu-ai-feed and from platform-specific cultural-tourism feeds for Bilibili, Douyin, and WeChat.

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

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

Provides clear operational context: data updates daily at 15:00 for the previous day, and dates without data must be confirmed before querying. It does not explicitly name alternatives or state when not to use this tool, but the context is specific enough that an agent can infer the appropriate scenario.

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 behavioral burden and does communicate the key behavior: it connects to the web and returns AI-formatted search results. However, it does not disclose potential limitations like freshness, source coverage, or response format, which would be useful for a search tool without annotation support.

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

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

The description is one compact sentence that front-loads the tool's core action and output. Every word contributes meaning, and there is no redundant or filler content.

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

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

For a single-parameter, no-output-schema search tool, the description adequately covers the main invocation flow: enter a question, get an AI search result. It could be more complete by noting expected result structure, but the simplicity of the tool makes this a minor gap.

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 documents inquiryText at 100% coverage with the description '搜索问题', so the tool description adds little beyond the schema. The phrase '输入问题' does reinforce the parameter's purpose but provides no extra formatting, constraints, or examples.

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

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

The description states a clear verb and resource: it performs DeepSeek AI web search and returns AI-generated search results for an input question. It also indicates the provider, which helps distinguish it from sibling search tools like doubao-websearch and kimi-websearch, though it doesn't explicitly describe those distinctions.

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

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

No guidance is given about when to use this tool versus the many sibling search tools, such as doubao-websearch, kimi-websearch, or toutiao-search. The description implies usage for general questions but lacks any exclusions or alternative-selection cues.

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 of behavioral disclosure. It discloses that the tool performs an online AI search and returns an AI search result, which covers the core behavior. It omits any caveats, output detail, or limitations, but for a stateless search tool the basic behavior is stated.

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?

One short, front-loaded sentence states the brand, the action, and the input/output behavior without filler. Every word 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?

For a tool with one fully documented parameter and no output schema, the description names the return value ('AI搜索结果') and the invocation pattern. It lacks a more concrete output structure or usage context, but is adequate for a simple 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 the baseline is 3. The single parameter inquiryText is already documented as '搜索问题'; the description's '输入问题' adds no new format, constraints, or semantic detail 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 states a clear action ('联网搜索') and resource ('豆包 AI'), and specifies the input/output contract: a question yields AI search results. It is unambiguous, but it does not explicitly differentiate doubao-websearch from sibling tools such as deepseek-websearch or kimi-websearch, so it falls short of full sibling distinction.

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 when-to-use or when-not-to-use guidance is provided. Given many sibling search tools (deepseek-websearch, kimi-websearch, toutiao-search, etc.), the agent is given no criterion for choosing this over 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 full burden. It discloses the high-level action (querying data and generating a report), but does not describe side effects, report contents, data freshness, required permissions, or any limitations. It adds minimal behavioral context beyond the obvious purpose.

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 clear, front-loaded sentence that immediately communicates the tool's purpose and its core behavior. 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?

Given the simple one-parameter schema, the description is adequate for basic invocation. However, there is no output schema, and the description does not clarify what the diagnosis report contains or how the agent should interpret the generated report, leaving some ambiguity about the tool's full behavior.

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 the schema already documents accountId as the Douyin account ID. The description only restates that account data is queried, adding no meaningful parameter semantics 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 states a specific verb and resource: querying Douyin account data and generating a diagnosis report based on account ID. This clearly distinguishes the tool as an account-level Douyin diagnosis tool, though it does not explicitly contrast it with sibling tools.

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

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

Usage is implied through the description: it is meant for diagnosing a Douyin account from its account ID. However, there is no explicit guidance on when to choose this tool over alternatives such as xiaohongshu-account-analyzer or kuaishou-accounts, and no exclusions or prerequisites are mentioned.

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

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 does well by revealing the automated daily scan, the selection criteria (interaction metrics), and the output form (HTML daily report with cover images and data metrics). However, it leaves ambiguity about what happens on invocation—whether it returns a report or sets up a subscription—and does not cover side effects or prerequisites.

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 earning its place: the first packs core capabilities (scan, filter, cluster, generate HTML report) efficiently, the second lists trigger phrases. No redundant wording or irrelevant detail.

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 explains the core deliverable (HTML daily report) and the selection logic, but with no output schema and no annotations, it leaves important call semantics unclear. For instance, it does not specify whether the tool returns the report directly or whether the '每日订阅' feature is activated automatically. The roles of pageNum/pageSize also remain vague, making the description incomplete for an agent deciding how to invoke 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?

Schema coverage is 100%, but the descriptions are just parameter names ('keyword', 'pageNum', 'pageSize') without added meaning. The tool description implies keyword refers to the AI topic being scanned, but it does not clarify how pageNum and pageSize affect the report. Since the high schema coverage warrants a baseline of 3 and the description adds only marginal parametric nuance, a 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 states a clear, specific function: scanning Douyin AI-related content daily, ranking by engagement, clustering, and generating an HTML report. This distinctively separates it from sibling tools like douyin-search or douyin-daily-hot. The resource (Douyin AI works) and the action (scan/filter/cluster/generate report) are both explicit.

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

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

The description gives concrete triggers: '当用户需要 AI 抖音日报、抖音AI热点、AI抖音内容、抖音信息源、douyin ai feed 时使用.' This provides clear context for when to use the tool. However, it does not explicitly state when not to use it or mention alternatives like douyin-daily-hot for general Douyin hot content, so it earns a 4 rather than a 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?

No annotations are provided, so the description carries the full disclosure burden. It only signals read-only behavior through '查询' and does not describe what the returned ranking contains, how surge is computed, whether startDate is necessary, or any response-shape details.

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 compact sentence that leads with the resource and follows with the purpose. It is appropriately brief, though the brevity comes at the cost of behavioral and contextual detail.

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

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

With no output schema and no annotations, the description should at least characterize the returned data and ranking behavior. It does not explain what fields are returned, how the date parameter affects results, or how this surge ranking behaves relative to other ranking tools, leaving an agent with significant 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 description coverage is 100%, so the schema already documents the type options and the startDate format. The description adds no parameter-specific meaning, which matches the baseline of 3 for fully covered 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 names a specific resource, the Douyin content surge ranking, and a concrete action: querying viral content with surging interaction data. It is clear and read-oriented, though it does not explicitly distinguish itself from closely related siblings such as douyin-weekly-surge or douyin-rise-ranking.

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 a use case but gives no explicit guidance on when to use this tool versus alternatives. With many sibling ranking tools present, there is no when-to-use or when-not-to-use guidance to help an agent route correctly.

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 behavioral burden. It only reveals that the tool is a read-style query ('查询'), but does not disclose what happens with empty parameters, how the date range behaves, what the 'type' values represent, or whether results are limited or paginated. The ordering-by-likes hint is useful but 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?

A single front-loaded sentence with no filler words; it states the tool name's subject and the query function efficiently. It could have used the brevity to also convey behavioral details, but as written it wastes no 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?

With no annotations, no output schema, and three loosely described parameters (including an ambiguous 'type'), the description is not complete enough for an agent to call the tool confidently in edge cases. The presence of zero required parameters is not explained, and the agent cannot know what a no-argument call returns or what valid type values exist.

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 the baseline is 3. The description adds marginal context by framing the date parameters as belonging to a 'daily' ranking, but it does not clarify the meaning of the 'type' parameter (no enum, only a default of '1') or whether startDate/endDate must be used together.

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-resource pair (查询/query + 抖音每日爆款榜/Douyin daily viral list) and adds a clear selection criterion: works ranked by highest daily likes. It is not a tautology of the name because the second clause adds the 'likes ranking' detail. However, it does not explicitly distinguish itself from closely related siblings like douyin-hot-trend, douyin-rise-ranking, or douyin-weekly-surge.

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 offers no guidance on when to use this tool versus alternatives, no named sibling tools, and no mention of prerequisites such as whether date parameters should be paired. An agent is given zero context for choosing this over the many other Douyin ranking/trend tools in the sibling list.

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 behavioral transparency burden. It discloses the main mode-switching behavior (empty vs. filled dates) but does not describe the return shape, what happens if only one date is supplied, range limits, pagination, or sorting behavior. 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 a single, front-loaded sentence with no filler. Every clause adds meaningful information: the resource, the default behavior, and the optional time-range capability.

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 two-parameter tool this is mostly adequate, but the lack of an output schema raises the burden on the description to clarify return expectations. It does not address edge cases like a single date being provided, and only vaguely indicates the output is '热门话题'. An agent could invoke it correctly, but some ambiguity remains.

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 valuable relational semantics by explaining that empty dates yield real-time results while filled dates query a specific period, reducing ambiguity around how the two optional parameters interact.

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

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

The description states a specific verb ('查询' - query) and resource ('抖音热点趋势' - Douyin hot trends), and clarifies two modes: real-time hot list without dates, and hot topics for a specified time period. It does not explicitly differentiate itself from siblings like douyin-daily-hot or douyin-rise-ranking, so it falls just short of a 5.

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

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

The description gives clear usage context: leave dates empty for the real-time hot list, or provide a date range for historical hot topics. However, it does not mention alternative tools or exclusions, so it lacks the explicit when-to-use-vs-alternatives guidance needed for a 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?

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only states what the tool detects ('敏感词') but does not explain what the output looks like, whether it returns the matched words, severity levels, suggestions, or just a pass/fail result. It also doesn't mention any limitations such as the word list being fixed or updated periodically.

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 that is front-loaded with the platform and purpose. It wastes no words, though it could add a bit more behavioral detail without becoming verbose.

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 no output schema and no annotations, the description is too thin. An agent does not know what the return result will be, whether the tool flags offending words or just returns true/false, or whether there are any platform-specific nuances. The sibling tool 'multi-wordcheck' might be a better candidate for multi-platform checks, but the description doesn't help an agent choose.

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 the single parameter 'content' is already documented as '待检测文案内容' (copy content to be checked). The description adds the context that it's for Douyin prohibited-word detection, but it doesn't add extra meaning beyond the schema, such as expected format, length limits, or language requirements. 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 a specific verb ('检测' / check) and resource ('抖音违禁词' / Douyin prohibited words), and the input schema confirms it takes copy text. However, it does not explicitly differentiate itself from the sibling 'xiaohongshu-prohibited-word' or the multi-platform 'multi-wordcheck', so it lacks direct sibling distinction.

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: use this when checking Douyin copy for prohibited/sensitive words. But there is no explicit when-to-use or when-not-to-use guidance, and no mention of alternatives like 'xiaohongshu-prohibited-word' or 'multi-wordcheck' for other platforms. Usage context is clear from the platform-specific name, but exclusions are missing.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only restates the query intent and does not disclose sort order, output format, pagination, or behavior when no ranking data exists for the given date.

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

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

The description is a single efficient sentence with no wasted words, front-loading the ranking concept before the action. It is appropriately concise for a simple query tool, though it sacrifices useful context for brevity.

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 three-parameter query where the schema covers 100% of the parameters, the description is minimally adequate. However, there is no output schema, no behavioral context, and no differentiation from sibling Douyin ranking tools, so the overall context remains incomplete.

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 the parameters are already documented in the schema. The description itself adds no parameter meaning beyond what the schema provides, and the vague 'category' field remains vague, but the baseline of 3 applies.

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

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

The description states a specific verb ('查询') and resource ('抖音涨粉榜', account follower-growth ranking) with a date qualifier. It is clear enough to be distinguished from sibling tools like douyin-daily-hot or douyin-top-account, though it does not explicitly compare itself to any alternative.

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

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

No guidance is given on when to use this tool versus the many other Douyin ranking/surge tools. The only implied context is '指定日期', but there are no exclusions, alternatives, or prerequisites, and no mention of how dateType interacts with the date.

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?

无任何注解，描述需承担全部行为披露责任。'热门爆款作品'这一范围限定是有效的行为信息——说明这不是全量搜索而是热门内容搜索；日期筛选也是行为特征。但未说明结果排序规则、'爆款'的判定标准、翻页行为或调用限制。

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?

描述仅两个短句、无冗余修饰，核心动作和范围控制在前端。首句'抖音作品查询工具'与工具名略有重复，但作为领域锚点可接受；第二句承载了主要信息量，整体精炼高效。

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?

对5参数、无输出schema的工具而言，基本调用方式是明确的：关键词必填、日期可选、分页参数有默认值。但无输出schema的情况下描述未提及返回内容形态（如视频数据、作者信息、热度指标），也未说明'爆款'筛选逻辑，agent难以预判结果结构。

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描述覆盖率为100%，所有5个参数（keyword、startDate、endDate、pageNum、pageSize）在schema中已有说明。描述中'按日期范围筛选'只是重复schema已有信息，但'热门爆款'为keyword参数提供了一点语义上下文（搜索目标限定为热门作品），整体处于基准水平。

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?

描述包含具体动词（搜索）、资源（抖音作品）和范围限定（热门爆款、按日期筛选），能清晰传达这是关键词搜索工具。在众多抖音相关兄弟工具中（douyin-hot-trend、douyin-daily-hot、douyin-top-account等），关键词搜索这一特性将其与feed/榜单/账号类工具区分开，但未明确指出具体不同于哪一兄弟工具。

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?

描述完全没有提及何时使用此工具或何时使用替代工具。面对大量抖音内容探索类兄弟工具（douyin-hot-trend、douyin-content-surge、douyin-ai-feed等），agent无法获知关键词搜索与热门趋势/feed流工具之间的选择条件，也没有任何排除性说明。

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 behavioral burden. It only says '查询' (query), implying a read operation, but doesn't disclose output format, whether a list/ranking is returned, data source, or any constraints such as requiring at least one parameter. This is thinner than expected for an annotation-free 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?

A single, front-loaded sentence: the core purpose comes first, followed directly by the matching criteria. There is no redundant or filler content.

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

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

For a simple two-parameter query tool with no output schema, the description is mostly adequate, but it leaves a practical gap: because both parameters are optional, it doesn't say whether at least one must be supplied or what happens if neither is provided. The return content is only vaguely described as '对标账号'.

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 are already documented in the schema with 100% coverage, so the baseline is 3. The description adds the useful nuance that accountId or accountName can be used to match, but adds no detail about precedence, required-at-least-one, or how the values are interpreted.

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 begins with '查询抖音相似账号' (query Douyin similar accounts), a specific verb and resource, and then specifies matching criteria '根据账号ID或名称'. Its 'similar account' function is distinct from siblings like douyin-account-diagnosis or douyin-top-account.

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 tool's unique purpose is implied by '相似账号/对标账号', so an agent can infer when to use it, but the description never explicitly states when to choose this tool over alternatives or any exclusions. It gives the matching basis (ID or name) but no usage conditions.

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

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

With no annotations provided, the description carries the full disclosure burden and does substantial work: it reveals the scheduled daily 9:00 auto-pull behavior, HTML report generation, that account IDs are embedded directly in automation commands without file storage, and the exact output fields (title, favorites, comments, shares, likes, publish time). It omits auth requirements, rate limits, and behavior at the 20-account cap, but the disclosed traits are far above average.

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 core purpose is front-loaded in the first clause, followed by ordered content on behavior, output format, use cases, and trigger words. It is slightly redundant ('生成 HTML 报告' and '自动生成精美 HTML 作品报告' both appear) but otherwise every sentence earns its place without excessive length.

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 6 parameters, no annotations, and no output schema, the description covers the essential ground: purpose, the 20-account limit, schedule, output format (HTML plus terminal/Markdown tables with listed fields), and use cases. The main gap is that none of the six parameters are mapped to their meanings, which an agent must infer from 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 coverage is nominally 100%, but every parameter description is tautological (e.g., 'pageNum' described as 'pageNum', and accountName typed as number), so the schema adds no real meaning. The description provides only indirect hints — subscribing via 抖音号 likely maps to shortId, and '账号 ID 直接内置于自动化命令中' relates to accountId/accountName — but never explicitly maps the six parameters, keeping this at the baseline of 3.

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

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

The description opens with '抖音账号订阅追踪 — 通过抖音号订阅账号（最多20个）', a specific verb (订阅/subscribe) paired with a resource (抖音账号/Douyin accounts) and an explicit scope cap (20 accounts). This clearly separates it from sibling tools like douyin-search, douyin-account-diagnosis, and douyin-top-account, which serve different purposes. The trigger words and use-case sentence reinforce what this tool uniquely does.

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?

'当用户订阅抖音账号、追踪抖音作品更新、监控抖音竞品账号时使用' states clear conditions for use, and the trigger words ('抖音订阅、抖音账') give operational signals an agent can key on. It does not name specific sibling alternatives or state when not to use the tool, so it stops short of a 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It only says the tool queries a ranking; it does not describe return format, pagination, permissions, rate limits, or whether the type parameter changes the result set. The single verb 查询 implies a read operation, but little else is disclosed.

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

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

A single, front-loaded sentence with no wasted words; though '头部账号榜' and '最具影响力账号排行' are near-synonyms, the description is appropriately compact for a simple query tool. It would earn a 5 if it added a useful usage hint while staying 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?

Without an output schema or annotations, the description should compensate by explaining what the agent will receive and how parameters like type and dateType affect results. It does neither. The sibling list contains several similar Douyin ranking tools, and the description provides no context to disambiguate among them.

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 the input schema already documents all three parameters (type, dateType, rankDate) with individual descriptions. The description adds no parameter-level meaning, but the schema does the heavy lifting, so the baseline of 3 is appropriate.

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

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

The description uses a concrete verb (查询) and a clear resource (抖音头部账号榜, 抖音最具影响力账号排行), so an agent can tell it queries a ranking of top Douyin accounts. However, it does not explicitly differentiate it from sibling Douyin ranking tools like douyin-rise-ranking or douyin-daily-hot, so it falls just short of a 5.

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

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

The description gives no guidance on when to use this tool versus alternatives. It does not mention that it is for influencer/account rankings rather than rising accounts or daily hot topics, nor does it reference sibling tools. The agent must infer applicability from the name alone.

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

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

With no annotations provided, the description carries the full burden of behavioral disclosure, but it offers only a single claim: it queries surging viral content for the week. It does not disclose what the ranking type parameter variations produce, how startDate interacts with the '本周' claim, output shape, pagination, or any rate-limit/auth considerations. Too thin for an unannotated tool.

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

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

The description is a single efficient sentence with minimal waste, front-loading the ranking name and then the clarifying query statement. The opening '抖音周突增榜' slightly mirrors the tool name, but the second clause earns its place by specifying the resource and surge/interval criteria.

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 being a simple two-parameter tool, key context is missing: the meaning and valid values of 'type', the relationship between startDate and the stated 'this week' behavior, and any differentiation from siblings. With no output schema to cover return values, the description should explain more about what constitutes the returned '爆款内容' and ranking semantics.

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 the baseline is 3. Both parameters have descriptions, with startDate's format clearly stated and the description's '本周' adding loose context for date relevance. However, 'type' remains vague ('榜单类型' with a default of '2' but no enum or value explanations), and the description does not clarify which types exist or what '2' means.

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

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

The description states a specific verb ('查询'), resource (本周互动数据突增的爆款内容 — this week's viral content with surging interaction data), and temporal scope ('本周' weekly), making the core function clear. However, it does not explicitly differentiate itself from closely related siblings like douyin-content-surge or douyin-rise-ranking, whose names imply overlapping 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 gives no guidance on when to choose this tool over the many similar Douyin ranking siblings (douyin-daily-hot, douyin-hot-trend, douyin-rise-ranking, douyin-content-surge). Usage context is only implied by the word '本周' — there is no when-not-to-use guidance or explicit alternative routing.

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

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

With no annotations, the description carries the full disclosure burden. It does reveal the search behavior, the default A-share domain, and that the result contains account and latest-article data. It stops short of explaining ranking criteria, pagination behavior, or any limits or permissions, so it is only moderately 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 a single efficient sentence with a parenthetical that packs in the domain, action, default, and returned data. There is no filler or redundancy, and the most identifying 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?

For a simple tool with two optional parameters, the description is mostly adequate: it identifies the returned data and the default keyword behavior. However, without an output schema or annotations, the exact response shape, ranking order, and offset semantics remain underspecified.

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 some semantic context to keyword by noting the default A股 domain and the expected output, but offset is only documented in the schema as '偏移量' and receives no additional explanation.

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

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

The description uses a specific verb (搜索), a clear resource (公众号账号排行), and a domain (A股), and even states the return contents (账号与最新文章数据). It is clearly more informative than the name alone, though it does not explicitly contrast itself with sibling tools such as wechat-top-account or stock-feed.

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 phrasing '按关键词搜索公众号账号排行（默认A股领域）' implies the intended use case: find WeChat public-account A-share rankings by keyword. However, there is no explicit guidance about when to prefer this tool over sibling ranking/search tools or 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?

There are no annotations, so the description bears full responsibility for behavioral disclosure. It only says 'download' and does not explain what the tool returns (file vs URL), whether authentication or rate limits apply, how invalid links are handled, or any side effects beyond the core action.

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

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

The description is a single, direct sentence with no filler or repetition. Every word contributes to the meaning, and the essential information is front-loaded in an appropriately minimal way for a one-parameter tool.

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

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

With only one parameter, no annotations, and no output schema, the definition is minimally viable: it names the action and the required input. However, it omits any description of the return value or behavior on error, which an agent would need to know to fully trust and use the result.

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

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

Schema description coverage is 100%, with the url parameter already described as 'Instagram视频链接'. The description's mention of '根据视频链接' adds no new meaning beyond the schema, so the baseline of 3 applies; there is no additional parameter context to compensate.

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

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

The description states a specific verb ('下载' / download), a specific resource ('Instagram视频'), and the input type ('根据视频链接' / based on video link). It clearly distinguishes this tool from sibling downloaders such as tiktok-video-downloader and youtube-video-downloader by platform.

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

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

No guidance is given about when to use this tool versus alternatives. The description does not mention exclusions, preconditions, or the conditions under which a user should choose instagram-video-downloader over a sibling downloader; the agent must infer this solely from the platform name.

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 states the core read behavior: paginated fetching by account and exact single-article fetching by UUID. However, it does not disclose potential side effects, authentication needs, rate limits, result ordering, or what happens when the account or UUID is invalid—gaps that would matter for an agent deciding how to invoke it.

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 compact sentence that front-loads the core purpose and then specifies the two retrieval modes. The parenthetical '蒸馏器素材采集' adds some project-specific context but does not bloat the text. Every essential clause 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?

For a tool with three parameters, full schema coverage, and no output schema, the description gives adequate but incomplete context. It explains the main query modes and required parameter, but does not clarify result shape, pagination defaults, or the relationship between offset and workUuid. These details are not covered elsewhere, leaving notable 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 description coverage is 100%, so the baseline is 3. The description reinforces the meanings of account (公众号微信号), offset (分页), and workUuid (精确获取单篇), but adds no new detail beyond the schema, such as pagination size, UUID format, or the interaction between offset and workUuid.

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 queries article lists from WeChat public-account investment influencers ('公众号投资大V文章列表'), identifying the resource and verb. It also distinguishes two usage modes: paginated list pulling by account and exact single-article retrieval by UUID. It doesn't explicitly name sibling alternatives, so some differentiation is inferred rather than stated.

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

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

The description implies when to use the tool: when needing a paginated article list for a specific WeChat public account, or a single article by UUID. However, it provides no explicit guidance about when not to use it or which sibling tool to choose instead, such as generic wechat-search or gzh-astock-top. The usage context is functional but not comparative.

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 disclosing behavior. It states the basic function and that the result is an 'AI search result', but it does not describe the result format, whether sources are included, or any operational constraints or limitations. The agent is left guessing about the 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?

The description is one short, front-loaded sentence with no filler. It states the brand, the action, the input, and the output in compact form. Every word 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?

For a single-parameter tool with no output schema, the description gives a high-level idea of input and output but not enough detail about the returned 'AI search result'. It also lacks usage context relative to sibling search tools, so it is minimally viable rather than 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 description coverage is 100%, so the schema already documents inquiryText as '搜索问题'. The tool description simply restates that the user provides a question ('输入问题') without adding new meaning. This matches the baseline of 3 for high schema coverage.

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

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

The description states a clear action and resource: 'Kimi AI 联网搜索' (Kimi AI online search) and the outcome '输入问题返回AI搜索结果' (input a question and return AI search results). It is specific enough to distinguish from video-downloader and feed tools, though it does not directly contrast with the sibling AI search tools like deepseek-websearch or doubao-websearch.

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

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

The description gives no guidance on when to use this tool versus the many sibling search tools. There are no exclusions, no mention of preferred scenarios, and no comparison to deepseek-websearch, doubao-websearch, toutiao-search, or other search-related siblings.

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

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

No annotations are provided, so the description carries the full burden. It does disclose the fuzzy-search behavior, return fields, and a downstream use for kwaiId, which is helpful. However, it does not mention pagination behavior, result limits, data freshness, authentication needs, or potential empty results. These are gaps for a tool that might be called programmatically.

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

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

The description is compact and front-loaded with the core purpose and return values, followed by explicit use cases and trigger words. The use-case list has some redundancy (e.g., '查快手账号' and '搜快手达人' overlap with the main purpose), but the overall structure is efficient and leaves little waste.

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

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

For a simple search tool with one required parameter and no output schema, the description covers the essential return items and even points to the sibling tool for works lookup. It is complete enough for an agent to call correctly, though it could be more explicit about pagination defaults. The schema already handles page/pageSize, so the absence of that detail in the description is acceptable.

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 the baseline is 3. The description adds the '模糊搜索' (fuzzy search) nuance for accountName, which is useful beyond the schema's plain '快手账号名称'. Page and pageSize are already fully documented in the schema, so no additional meaning is needed there. Overall, the description adds only marginal semantic 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 states a specific verb ('搜索'), resource ('快手账号'), and mechanism ('通过账号名称模糊搜索'), and lists concrete return fields (kwaiId、昵称、头像、简介). It also distinguishes itself from the sibling kuaishou-account-works tool by explicitly noting that kwaiId can be used to query the account's works list. The trigger words further reinforce the intended use.

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

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

The description clearly states when to use this tool: '当用户需要按名称搜索快手账号、查找快手博主、定位达人账号、获取账号kwaiId时使用'. This provides explicit context for invocation. However, it does not explicitly mention when not to use it or name alternative sibling tools (e.g., kuaishou-search), though the kwaiId-to-works pointer indirectly helps route to kuaishou-account-works.

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. The word '查询' implies a read operation, but nothing is said about response structure, pagination caps, accepted ID format, authentication needs, or what fields a '作品' item contains. The description adds essentially no behavioral context beyond the query intent.

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?

A single eight-character clause with zero filler; the action and target are front-loaded and immediately scannable. It is appropriately compact for a simple paginated list query, though slightly more structure (e.g., a note on output or usage context) would have cost little.

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

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

With no output schema and no annotations, the description bears extra responsibility, and it only states that a works list is returned without describing its shape. For a simple 3-parameter paginated query with fully documented params, this is near-adequate for invoking the tool, but it leaves open how to source the userId and what the returned list contains.

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

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

Schema description coverage is 100%, with page, size, and userId all documented in the schema. The description's '按账号' merely restates the userId concept and adds the 'list' interpretation, but contributes no format, constraints, or relationships beyond what the schema already provides. The baseline of 3 applies because 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 '快手账号作品查询，按账号查询作品列表' states a specific query action and a clear resource (a Kuaishou account's works list), going beyond a restatement of the tool name. It does not explicitly differentiate itself from siblings like kuaishou-accounts or kuaishou-video-extract, but the '按账号查询作品列表' phrasing makes the core scope 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 offers no guidance on when to use this tool versus alternatives, and no exclusion criteria or prerequisites. With four Kuaishou-related siblings (kuaishou-accounts, kuaishou-search, kuaishou-comment, kuaishou-video-extract), an agent is left to infer the selection rationale, and there is no hint about how to obtain the required userId.

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, but it only says '查询' (query) and names the target. It does not disclose pagination behavior via the cursor, return format, sorting, or any rate limits or auth requirements, even though the cursor parameter implies paginated fetching.

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 six-character noun phrase that functions more as a title than an explanation. It is concise with no filler, but it is under-specified and does not provide the structural clarity expected of a tool description.

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?

There is no output schema and no annotations, so the description should explain what the tool returns and how pagination works. It only names the resource, leaving the agent to guess whether the output is a list, includes user info, or how cursor-based paging behaves.

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 the baseline of 3 applies. The description adds no extra meaning about the opusId format or how the cursor should be used, but every parameter is already documented in the input schema, so the description does not need to compensate.

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

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

The description states a clear query operation ('查询') on a specific resource ('快手作品评论'), and the tool name makes the platform and resource explicit. It is unambiguous enough to distinguish from siblings like bilibili-comment or twitter-comment by platform, though it doesn't specify whether results are a list of individual comments or an aggregate.

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 such as kuaishou-account-works or kuaishou-search, nor any prerequisites like how to obtain an opusId. The usage context must be inferred entirely from the tool name and input schema.

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

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

No annotations are provided, so the description must carry behavioral disclosure. It does disclose key behavior: searching returns work stats, links open details, and it can extract video details and copy. However, it does not mention output format, pagination behavior, rate limits, or whether any authentication or permissions are required, which leaves some transparency 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 efficient and front-loaded with the primary purpose, followed by output fields and usage triggers. The trigger-word list is somewhat redundant with the usage sentence, but overall every sentence contributes useful orientation.

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 4-parameter tool with no output schema and no annotations, the description covers purpose, result fields, and usage context. However, it omits the accepted sort values and the meaning/effect of page and size, which are required for an agent to invoke it correctly with multi-dimensional filtering.

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 reported at 100% but the property descriptions are mere labels ('keyword', 'page', 'size', 'sort') with no real meaning. The description adds semantics for keyword ('输入关键词') and partially for sort ('按排序方式多维度筛选'), but page and size remain unexplained. This fits the baseline of 3 for high schema coverage.

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

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

The description states a specific verb and resource: searching Kuaishou works, specifically '热门作品（广域库）'. It enumerates the returned fields (title, author, play count, likes, comments, favorites) and the ability to jump to details and extract video content. This clearly separates it from sibling tools like kuaishou-account-works or kuaishou-comment.

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

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

The description explicitly states when to use it: when the user needs to search Kuaishou works, find hot content, or query work data, and even lists trigger words. It lacks an explicit when-not-to-use or named alternatives, but the use case is clear enough to route an agent correctly.

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

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

With no annotations provided, the description carries the full disclosure burden. It does disclose the core behavioral trait — the video-to-text transformation happens automatically upon link submission. However, it does not reveal the output format, whether transcription or subtitle extraction is used, processing constraints (e.g., video length, public access), or failure behavior, which matters more given zero annotation coverage.

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 compact sentence that front-loads the core purpose, adds a clarifying parenthetical, and then gives the usage instruction. Every element earns its place with zero redundant wording.

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, the description adequately specifies the input and the action (link in, extracted copy out), which is enough for an agent to invoke it. However, with no output schema present, the description should ideally clarify what the returned text looks like (plain transcript vs. structured segments) and any limitations, leaving a moderate gap.

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

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

Schema description coverage is 100%, with the url parameter already described as "快手视频链接" (Kuaishou video link). The description adds the semantic that this link triggers automatic copy extraction, but it mostly echoes the schema rather than extending it, so the baseline 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 states a specific verb and resource: "提取文案" (extract copy) from "快手视频" (Kuaishou video), reinforced by the clarifying parenthetical "视频转文字" (video to text). This clearly differentiates it from sibling tools like kuaishou-account-works, kuaishou-comment, and the various platform video downloaders, none of which convert a video link into a transcript.

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

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

The description gives a clear invocation pattern — "提交视频链接自动提取文案" (submit a video link to automatically extract copy) — establishing that this tool is used when the agent possesses a Kuaishou video URL and needs its text content. However, it never explicitly names alternatives or states when-not-to-use conditions, so the guidance is clear context without exclusion logic.

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 present, the description must carry behavioral disclosure on its own. It does add useful context: '数据每日15:00更新前一天' and the platform-number mapping. However, it does not disclose authentication needs, rate limits, default behavior when no date is provided, or the structure of the returned top-50 results. This is adequate but shallow for a tool with zero annotation coverage.

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

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

The description is compact and well-structured: purpose first, then platform codes, then update cadence. Every sentence carries information relevant to invoking the tool correctly. It is slightly dense, especially with the platform-code list, but it avoids redundancy and front-loads the primary 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?

For a tool with no output schema and no annotations, the description should compensate by clarifying return structure. It hints at results via 'Top50榜单' and '爆款作品', but doesn't specify whether the list is per-platform or combined, what fields are returned, or how keyword filtering affects results. The update schedule and platform list are valuable, but the absence of output details leaves noticeable 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 coverage is 100%, but the description adds essential meaning for the 'platforms' parameter by mapping numeric codes to platform names (0公众号, 1抖音, 2视频号, 3小红书, 4快手, 6B站). The date and keyword parameters gain no additional explanation, but the platform-code mapping is a substantial enhancement over the bare schema. This lifts the score above the baseline of 3.

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

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

The description opens with '全网内容出海Top50榜单查询', a specific verb (查询) and resource (Top50 list of content going overseas), and then enumerates the six covered platforms. This clearly distinguishes it from single-platform sibling tools like douyin-ai-feed or bilibili-keywords-search. The platform list and 'Top50榜单' scope make the tool's 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 context ('按日期获取', '数据每日15:00更新前一天') but gives no explicit when-to-use or when-not-to-use guidance. It does not mention alternatives or exclusion criteria, so an agent must infer from the multi-platform scope why this tool should be chosen over platform-specific siblings. This is a significant gap.

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 exist, so the description bears the full burden. It only says 'returns detection results' without clarifying the output format, whether it blocks on sensitive words, or how multi-platform results are aggregated. This is a thin disclosure for an unannotated tool.

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

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

The description is a single efficient sentence that front-loads the core purpose. There is no wasted wording, though it is arguably too sparse to cover behavioral details.

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

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

Given the simplicity of the two-parameter schema, the description is minimally adequate, but with no output schema and no annotation, the vague 'returns detection results' leaves the agent unsure of what the response looks like. More detail about multi-platform result structure would improve 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 description coverage is 100%, with both 'content' and 'platform' clearly described in the input schema. The description adds no new parameter-level meaning beyond what the schema already provides, so the baseline 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 states a specific verb (detect) and resource (prohibited/sensitive words in copy), and the 'multi-platform' qualifier differentiates it from single-platform siblings like xiaohongshu-prohibited-word, douyin-prohibited-word, and wechat-prohibited-word. However, it does not list which platforms are covered, so it stops short of being fully precise.

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 word 'multi-platform' implies this tool is for checking across multiple platforms, but the description gives no explicit when-to-use guidance, no exclusions, and no mention of alternatives. Usage context is inferable but not stated.

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 disclosure burden. It reveals the daily 15:00 update schedule, the previous-day data lag, the strict date-validity rule, and the no-automatic-fallback behavior. It does not describe the output shape or error behavior, but those are secondary for a simple read-only feed query.

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 compact sentence that front-loads the purpose and sorting behavior, then packs the important update and date rules without redundancy. Every phrase 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?

For a low-complexity tool with two optional parameters, a fully documented schema, and no output schema, the description provides all essential operational context: platform, content type, ordering, update cadence, and date constraints. Nothing critical is missing for correct 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 coverage is 100%, so the baseline is 3. The description adds meaningful semantics to the date parameter: it must not exceed the latest data date and no-data dates must be confirmed before querying. The count parameter receives no additional description beyond the schema, preventing a 5.

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

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

The description states a clear verb-resource pair: query Bilibili short-drama hit-list works by date, sorted by likes. It distinguishes itself from sibling tools like playlet-douyin-feed and general bilibili search/download tools by naming both the platform (B站) and the content type (短剧爆款榜).

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 gives explicit usage constraints: dates must be ≤ the latest data date, no-data dates require confirmation, and automatic fallback is prohibited. It does not explicitly name alternative tools when not to use it, but the sibling names and platform/content scoping make the selection context reasonably 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 and does disclose important behaviors: the daily 15:00 update schedule, the restriction on querying future dates, and the critical rule that dates without data require confirmation and cannot auto-fallback. This goes well beyond a generic query description, though it stops short of describing response format or error handling.

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?

A single dense sentence front-loads the purpose and then adds only high-value behavioral constraints. Every clause carries operational information with no filler or repetition of schema fields.

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

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

For a simple two-parameter query tool with no annotations and no output schema, the description covers the essential calling semantics: what is returned, when data is fresh, and the non-obvious date/fallback rules. It doesn't describe the response shape, which would be useful given there is no output schema, but for invoking the tool correctly it is nearly sufficient.

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

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

The schema already documents both parameters at 100% coverage, so the baseline is 3. The description adds genuine value for the date parameter by specifying data freshness semantics and the allowed range, plus the no-fallback rule. The count parameter is not enriched, but the overall parameter semantics are meaningfully improved.

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

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

The description states a specific verb ('查询/获取') and resource ('抖音短剧作品'), and specifies the ordering ('点赞量排序') and filter ('按日期'). This makes the tool's core function clear and it can be distinguished from other playlet feeds by platform and content. However, it never explicitly names a sibling tool or states what it is not, so explicit differentiation is missing.

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

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

The description gives concrete operational constraints for the date parameter (must be ≤ latest data day, no automatic fallback, confirm no-data dates), which is useful. But it provides no guidance on when to choose this tool over sibling alternatives like playlet-bili-feed or douyin-daily-hot; the use case is only implied by the name and platform focus.

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 reveals important behavior: daily update timing, strict date-boundary rule, and the no-auto-fallback policy. It doesn't describe response format or error behavior, but the key operational traits are disclosed.

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

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

The description is a single dense sentence with no filler. Every clause contributes either resource identification, sorting behavior, data freshness, or a constraint. The purpose is front-loaded and the constraints are compactly packed.

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 two-parameter read-only feed query with no output schema, the description covers the resource, sort order, data freshness, date constraints, and the no-fallback rule. It doesn't enumerate return fields, but the nature of a ranked article list is reasonably inferable and not essential for invocation.

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

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

Schema coverage is 100%, so the schema already documents both date and count. The description adds meaningful semantic value for the date parameter: allowed range relative to the latest data day, update freshness, and the requirement to confirm no-data dates rather than silently fall back. Count is sufficiently covered by 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 names a specific verb and resource: 查询公众号短剧爆款榜 (query WeChat official-account short-drama hit list), and adds distinguishing attributes: by date, sorted by read count. This clearly differentiates it from sibling platform feeds like playlet-douyin-feed or cultural-tourism-wechat-feed.

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

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

The description gives concrete operational guidance: data updates at 15:00 for the previous day, query date must be no later than the latest data date, no-data dates must be confirmed before querying, and automatic fallback is forbidden. It doesn't explicitly name alternative tools or state when not to use this tool, so it stops short of a 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?

With no annotations, the description carries the full burden and discloses the key behaviors: the 15:00 update schedule, the date-validity boundary, and an explicit prohibition on automatic date fallback ('禁止自动回退'). The no-fallback rule is especially valuable because it stops an agent from silently substituting an earlier date. It does not disclose return format or error behavior, but the critical operational traits are covered.

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

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

Two sentences with the tool's purpose front-loaded before its constraints. Every clause earns its place. The second sentence is dense, packing three constraints into one run-on clause, which slightly harms readability, but there is no wasted text.

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

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

The trickiest aspects for correct invocation — update cadence, date validity, and the no-fallback rule — are well covered, and both parameters are fully documented in the schema. However, with no output schema, the description does not explain the return format or what the response contains beyond 'notes sorted by interaction', and the instruction '无数据日期必须确认后再查' is ambiguous about what 'confirm' means and with whom.

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 genuine meaning beyond the schema by stating the date parameter's allowed range (≤ latest data date), the confirmation requirement for no-data dates, and the no-fallback rule — none of which appear in the schema's parameter descriptions. The count parameter is already fully documented by 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 states a specific verb and resource: query Xiaohongshu short-drama notes by date, sorted by interaction volume. The qualifiers '短剧' (short drama), '互动量排序' (interaction sort), and the platform name distinguish it from most siblings implicitly, though it never explicitly contrasts itself with similar tools like playlet-douyin-feed or xiaohongshu-dailytop.

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

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

The description gives clear operational context: data updates daily at 15:00 for the previous day, dates must be ≤ the latest data date, and no-data dates require confirmation. However, it provides no guidance on when to choose this tool over the many similar siblings (playlet-bili-feed, playlet-douyin-feed, xiaohongshu-dailytop, xiaohongshu-ai-feed), so selection among alternatives is left to inference.

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 disclosure burden. It does disclose an important runtime behavior: the tool automatically waits for the task to complete and then returns a video link. However, it does not mention potential wait duration, failure modes, pricing, or credit implications, so the disclosure is partial.

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 compact sentence with no filler. It front-loads the tool purpose, adds the model identity, and ends with the most operationally relevant behavior: waiting for completion and returning the link.

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?

There is no output schema, and the description does state the return type: a video link. It also covers the key operational behavior of automatic waiting, which is the main uncertainty an agent would face. Detailed parameter choices are left to the fully described schema, so the description is sufficient even though it does not summarize image-to-video support.

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 the baseline is 3. The description adds little parameter-level meaning beyond restating that text prompts are the input, and it omits the image-to-video capability obvious from the imageUrl parameter, though the schema already documents that.

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

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

The description states a specific action and resource: generate video from a text prompt using the Doubao Seedance 2.0 model. It clearly distinguishes this tool from the sibling set, which contains mostly downloaders, search tools, feed aggregators, and content writers rather than video generators.

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: use this tool when the agent needs to generate a video from a prompt. It does not explicitly name alternatives or when-not conditions, but no sibling tool appears to offer the same video generation capability, so an explicit exclusion is less critical.

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 behavioral disclosure burden. It discloses that results are sorted by publish time descending and that arbitrary account IDs are supported. However, it does not describe output fields, pagination behavior, rate limits, or empty/failure cases.

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

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

The description is compact and front-loaded with the core purpose, followed by a useful built-in account list. No redundant sentences, though the account list makes it slightly long.

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 parameter schema is complete and the description covers purpose, scope, sorting order, and valid account sources. However, with no output schema and no annotations, the return structure and pagination details are unspecified, leaving some ambiguity for the agent.

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

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

Schema coverage is 100%, so the baseline is 3. The description adds value by listing concrete built-in account IDs for the required `account` parameter, giving the agent valid callable examples. The `days` and `offset` parameters are already fully described 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: querying historical WeChat official-account articles by account ID for A-share big-V accounts. It gives a specific verb-resource pair ('获取其历史文章') and includes concrete built-in account IDs, which distinguishes it from sibling search, feed, and top-list 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 provides clear usage context: it is for review/stock-picking material collection and should be used when querying articles by WeChat account ID. It also clarifies support for arbitrary account IDs, but it does not explicitly name alternatives 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?

No annotations are provided, so the description carries the full burden. It signals read-only behavior via '查询' and an output focus on '爆款内容', but it does not disclose return format, platform coverage, pagination, freshness, or limitations.

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?

One sentence with no filler and the core operation front-loaded. There is mild redundancy between '股票内容资讯查询' and '跨平台搜索股票相关爆款内容', but it remains concise and scannable.

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 no annotations and no output schema, so the description should explain what the returned content looks like and which platforms are included. It only says 'content info query' and 'viral content', leaving the agent to guess return structure and cross-platform scope.

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 the baseline is 3. The description adds no parameter-specific detail beyond the stock-content theme; it does not clarify platform values, date formats, or keyword behavior beyond what the schema already states.

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

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

The description states a specific operation: querying stock-related news/content and cross-platform search for viral stock content. It distinguishes itself from platform-specific feed siblings and stock-analysis, though it does not explicitly name an alternative.

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 when-to-use or when-not-to-use guidance is provided. The cross-platform phrasing implies one usage context, but with many similar search/feed siblings, there is no explicit comparison or exclusion.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only restates the core action of downloading a video and gives no details about output format, whether it returns a file path or URL, potential failures, authentication requirements, or platform restrictions. This is a significant transparency 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 a single front-loaded sentence with no wasted words; it directly communicates verb, object, and input. However, it is somewhat terse and borderline under-specified, which keeps it just below a perfect score.

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 single-parameter tool, the description is minimally adequate: the action and the required input are clear. But with no output schema and no annotations, the tool's expected result or behavior after invocation is not explained, leaving an agent to guess what the response will contain.

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 has 100% coverage with the parameter description 'TikTok视频链接', so the baseline is 3. The description adds no additional parameter meaning beyond reinforcing that the URL must be a TikTok video link; it does not clarify allowed URL formats or whether share links are accepted.

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

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

The description states a specific verb ('下载' / download), a specific resource ('TikTok视频'), and the input condition ('根据视频链接' / based on a video link). It clearly differentiates from sibling video downloaders for other platforms like bilibili, youtube, or xiaohongshu by naming TikTok explicitly.

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

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

The description implies when to use the tool: when a user provides a TikTok video link and wants it downloaded. However, it provides no explicit guidance about when not to use it, nor does it reference any alternative sibling tool, so the usage context is only implied rather than stated.

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?

Annotations are absent, so the description carries the full burden of behavioral disclosure, and it is thin. It discloses only that this is a keyword-based search, with no mention of pagination semantics (despite the offset parameter), result scope/filtering behavior, rate limits, or whether '爆款' is an actual filter or aspirational phrasing. The description neither confirms nor clarifies what happens when the search executes.

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

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

The description is a single front-loaded sentence: platform first, then the action and query method. Every element earns its place, and there is zero filler. It could have used the saved space for behavioral context, but as a concise and well-ordered definition it is effective.

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 low-complexity tool with two flat parameters, the description is adequate for basic invocation — an agent can determine it needs a keyword and can call the tool. However, with no output schema and no annotations, the missing return-format and pagination details are meaningful gaps, and the ambiguous '爆款内容' phrasing adds uncertainty about what results to expect.

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% (both offset and keyword have Chinese descriptions), so the baseline is 3. The description's '按关键词查询' corroborates the keyword parameter's role but adds no new meaning; it does not explain the offset parameter's pagination behavior or any keyword formatting constraints, leaving agents with only the terse schema text.

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

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

The description states a specific verb (搜索/search), a resource (今日头条作品/Toutiao works), and a method (按关键词/by keyword), making the core purpose clear. The platform designation '今日头条' distinguishes it from the many sibling platform-search tools (douyin-search, kuaishou-search, wechat-search, etc.). However, '爆款内容' (viral content) creates slight ambiguity about whether the tool searches all Toutiao content or only filters for trending/viral items.

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

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

No guidance is given on when to use toutiao-search versus alternatives. With roughly a dozen sibling search tools (weibo-post-search, wechat-search, xiaohongshu-search, deepseek-websearch, doubao-websearch, etc.), the description does not state which platform scenarios map to this tool, when not to use it, or how it differs from general web-search siblings. An agent must infer platform selection purely from the tool name.

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 implies a read-only aggregation query, but it does not describe return shape, default behavior when no parameters are supplied, whether date ranges are required, or any operational constraints. This is minimal and insufficiently 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 a single, front-loaded sentence with no filler. There is slight redundancy between '热点' and '热门话题', but overall it is compact and scannable.

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 annotations, no output schema, and many closely related siblings, the description is too thin. It omits expected output format, default behavior, differentiation from hot-topic alternatives, and operational caveats. Parameter documentation is complete, but that alone does not make the tool contextually 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 description coverage is 100%, so the baseline is 3. The description's mention of platform and keywords reinforces the schema but adds no new semantic detail beyond what each parameter already documents.

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

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

The description clearly states a query/retrieval operation ('查询'/'获取') applied to a resource ('全网热点'/'热门话题') with explicit filters ('平台和关键词'). It is clear enough to distinguish from platform-specific hot-topic tools, but it does not explicitly differentiate itself from closely related siblings like trending-hub-top10.

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 about when to prefer this tool over alternatives such as trending-hub-top10, douyin-daily-hot, or weibo-hot-search. It does not state exclusions, prerequisites, or typical use cases, which is a notable gap given the large set of sibling tools.

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

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only indicates a read-only 'query', but does not disclose whether date parameters are required, what happens when they are omitted, how the TOP10 is determined, or any ranking/period 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 a single short sentence with no filler and the core scope is front-loaded. It is concise and easy to parse, though its brevity contributes to gaps covered in other dimensions.

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 output schema and no annotations, the description leaves an agent without return-format context, date-range behavior, or any caveats about how the TOP10 is computed. It is enough to identify the tool's purpose, but not fully sufficient for correct invocation in nuanced user requests.

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

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

Schema description coverage is 100%, with both startDate and endDate described as date strings in YYYY-MM-DD format. The description adds no additional parameter semantics, so the baseline score of 3 is appropriate.

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

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

The description states a specific operation ('查询' / query) over a clear resource ('全网热搜关键词 TOP10'). It clearly identifies the tool as a cross-network top-10 hot-search keyword query, though it does not explicitly distinguish it from the sibling tool 'trending-hub' or other platform-specific hot-search 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 provides no guidance on when to use this tool versus alternatives like 'trending-hub', 'weibo-hot-search', or 'douyin-daily-hot'. The only implicit usage signal is the '全网' scope, but no exclusions or selection criteria are given.

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?

There are no annotations, so the description must carry the full behavioral burden. It only says 'query', implying a read operation, but does not disclose return format, pagination, authentication needs, or rate limits. This is minimal and leaves important behavior unspecified.

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

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

The description is a single compact phrase with no filler, and the platform/resource are front-loaded. It is efficient, though slightly under-structured as a noun phrase rather than a complete sentence.

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

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

With no output schema and no annotations, the description should explain what the tool returns (e.g., comment list, fields, pagination) but does not. It also gives no usage context beyond the basic query, so an agent cannot fully anticipate the result or invocation requirements.

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% coverage and describes tweetId as '推文ID', so the description adds little beyond the schema. The baseline of 3 applies because the sole parameter is already documented and no extra format or constraint is clarified.

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

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

The description states a clear action (query) and resource (tweet comments on X/Twitter), and explicitly names the platform, which helps distinguish it from siblings like youtube-comment or kuaishou-comment. It does not mention the required tweetId parameter, but the core purpose is identifiable.

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. The description does not mention sibling comment tools or give conditions such as 'use this for X/Twitter comments' or 'for other platforms use youtube-comment/kuaishou-comment.'

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 states the core behavior but does not reveal what the tool returns (direct video URL, file path, success message), whether it creates side effects on disk, any authentication needs, or how invalid or non-video tweets are handled. This leaves significant behavioral ambiguity.

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?

One short, front-loaded sentence with no filler. It immediately communicates the action, target platform, and input requirement. Perfectly sized for a simple single-purpose tool.

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

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

The tool has one well-documented parameter and a straightforward action, making the input requirement complete. However, since there is no output schema and no annotations, the description does not explain the return value or output contract, leaving some ambiguity for the agent about interpreting the result.

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%: the single parameter 'url' is already described as 'X(Twitter)推文链接' (X/Twitter tweet link). The tool description merely restates this concept ('根据推文链接') without adding new semantic meaning, so the baseline of 3 applies.

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

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

The description states a specific verb (下载/download), a specific resource (X(Twitter)视频/X(Twitter) video), and the required input condition (根据推文链接/from a tweet link). This clearly distinguishes it from sibling downloaders for Instagram, TikTok, YouTube, and 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?

The intended usage is implied by the name and description: use this tool to download a video from an X/Twitter tweet link. However, there is no explicit guidance on when to use it versus alternatives, no exclusions (e.g., unsupported URL types), and no prerequisites such as public visibility or specific tweet URL formats.

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 behavioral burden and does disclose the core flow: compose a prompt, then generate an MP4, plus problem diagnosis. However, it omits important traits such as whether generation is synchronous, how results are returned, or any limits/costs, so transparency is only moderate.

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 short and front-loads the main purpose, but the trigger-word list is redundant for an API tool definition and the '多种创作场景与问题诊断' sentence is vague filler. It is not bloated, but not 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?

With 10 optional parameters, no output schema, and no annotations, the description is far too thin to let an agent know how to construct a valid call or what to expect in return. It provides no details on parameter effects, return format, or failure modes.

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 the schema coverage is nominally 100%, every parameter description merely repeats the parameter name (e.g., 'seed', 'model'), providing no real meaning. The tool description adds no guidance on valid values, units, or how optional parameters like ratio, generateAudio, or executionExpiresAfter should be used.

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 writes professional AI video prompts and directly generates MP4 videos, which is a specific verb+resource combination. It also mentions multiple creative scenarios and problem diagnosis, giving a clear sense of scope, though it does not explicitly distinguish itself from sibling generation/writing tools like seedance-video-gen.

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 lists trigger words and says it supports multiple creation scenarios, implying broad applicability, but it gives no explicit guidance on when to prefer this tool over the many sibling video/writing tools. There are no stated exclusions, prerequisites, or alternative routing conditions.

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

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

With no annotations, the description carries the full behavioral disclosure burden. It does disclose one important trait: '自动等待任务完成' (automatically waits for task completion), which tells the agent the tool handles asynchronous work internally. However, it does not mention failure behavior, rate limits, costs, or what happens when a reference image is invalid, so behavioral disclosure is only partial.

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 compact sentence with purpose front-loaded, followed by key capabilities and the auto-wait behavior in parentheses. There is no filler, no repetition of the tool name, and every clause contributes useful information.

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

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

For a 4-parameter tool with no output schema, the description frames the operation adequately but leaves gaps: it does not specify the return shape, clarify the dependency between style=reference and referenceImage, or explain whether '批量风格' means multiple outputs in a single call. The schema covers parameter syntax well, but the absence of an output schema raises the need for more behavioral 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 description coverage is 100%, so the schema already documents all four parameters, including style enum meanings and referenceImage usage. The description adds only high-level feature hints like '参考图' and '批量风格' but does not clarify whether referenceImage becomes required when style=reference or how batch styles are represented in a call.

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

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

The description states a clear verb-resource pair: '提交文字提示词生成图片' (submit a text prompt and generate an image), and adds the use case '视觉运营文案配图'. It is unambiguous as an image-generation tool, but it does not explicitly name or differentiate from sibling tools like seedance-video-gen, so it stops just short of a 5.

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

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

The description implies when to use it ('视觉运营文案配图' for visual operations copy illustrations) and how to use it ('提交文字提示词生成图片'), but it gives no explicit when-not-to-use guidance or alternatives. The usage context is clear enough to infer, but exclusions are absent.

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 of behavioral disclosure. It does convey a read-only lookup of 100k+ read articles filtered by category and date, but it does not disclose result format, result limits, sorting behavior, or handling of invalid date/category values.

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

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

The description is one short sentence with the main action front-loaded and no filler. It is slightly redundant in that '公众号10w+爆文查询' and '获取10w+阅读热门文章' restate the same core idea, but this is minor.

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 3-parameter query tool, the core inputs and selection criteria are documented. However, with no output schema and no annotations, the description still leaves the agent without a clear picture of the return payload or any usage constraints, so it is only minimally 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 description coverage is 100%, so the baseline is 3. The description only repeats the 'by category and time' idea already present in the parameter schema and adds no additional format, relationship, or default-value 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 names a specific action (查询/获取) and resource (公众号10w+爆文/10w+阅读热门文章) and states the key filtering scope: category and time. It is clearly distinguishable from WeChat sibling tools by the '10w+' threshold and category/time focus.

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

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

The description gives no when-to-use guidance, no exclusions, and no mention of alternatives. Among many related WeChat tools, the agent is left to infer when this tool should be chosen over tools like wechat-original-hot or wechat-search.

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 meaningful behavior: daily automatic scanning, engagement-based filtering, clustering, HTML report generation, cover images, metrics, and daily subscription. It does not discuss side effects or output structure, but the described behavior is substantial and non-misleading.

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 well-structured sentence that front-loads the core function, lists key features, and ends with explicit usage triggers. Every part earns its place, and there is no redundant or filler wording.

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 conveys the tool's high-level behavior and use case, but with no output schema and no parameter semantics, an agent still has to infer how to supply keyword, pageNum, and pageSize. It also does not explicitly contrast this tool with very similar siblings such as wechat-channels-crawler or the other ai-feed tools, leaving some selection ambiguity.

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 the baseline is 3. However, the schema descriptions are near-tautological ('keyword', 'pageNum', 'pageSize'), and the tool description adds no parameter-specific guidance about what keyword should contain or how pagination interacts with the daily report. The parameter names are self-explanatory to a degree, but the description does not enrich them.

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

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

The description clearly states a specific verb and resource: it automatically scans WeChat Channels for AI-related works, filters by engagement metrics, clusters them, and generates an HTML daily report. This makes the tool's purpose concrete and distinguishes it from generic siblings like wechat-channels-crawler or platform-specific feeds such as douyin-ai-feed.

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 trigger conditions: use when the user needs AI video account daily reports, AI hotspots from video accounts, AI video account content, or a video account information source. It does not explicitly name alternatives or when not to use, but the context is clear enough for an agent to select this tool.

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

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

With no annotations, the description carries the disclosure burden. It reveals that the tool searches by keyword, supports multiple sort orders, and returns results as a structured table. However, it does not mention pagination behavior, data limits, freshness, or any constraints of the crawler.

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

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

The description is well organized: it opens with the tool's core purpose, then explains supported behavior and output, followed by clear use cases and trigger words. The trigger-word list adds routing value without being overly verbose.

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?

There is no output schema and no annotation coverage, so the description must fully explain how to call the tool correctly. It leaves page/size semantics unspecified, does not map sort modes to parameter values, and only vaguely describes the return as a structured table.

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%, but each parameter description is tautological ('keyword', 'sort', 'size', 'page'). The description adds meaning for keyword and sort dimensions, but it does not specify exact sort values or the units/ranges for page and size.

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

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

The description states a specific verb and resource: searching WeChat Channels (视频号) works by keyword, with sorting modes and structured table output. It is distinguishable from generic wechat-search by focusing specifically on Channels video data, though it does not explicitly name sibling tools.

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

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

The description provides explicit when-to-use scenarios: finding hot content, searching viral videos, querying video data, or understanding content performance on WeChat Channels. It includes trigger words to help route intent, though it does not state when not to use it 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 are provided, so the description carries the full burden of behavioral disclosure. It suggests a read/query operation and mentions returning '封面设计参考', but it does not clarify whether the output contains actual cover images, article links, design suggestions, or other data, nor does it disclose any limitations or side effects.

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

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

The description is a single concise sentence that front-loads the core purpose. It loses a point because '爆款封面参考' and '封面设计参考' are somewhat redundant, but overall it is compact 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?

With no output schema and no annotations, the description should explain what the caller receives. It only says the tool provides cover-design reference, leaving the return structure, item format, and any default behaviors unclear. The schema documents parameters adequately, but the overall context is incomplete for confident invocation.

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

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

Schema description coverage is 100%, so the schema already documents keyword, maxItems, and startDate. The description adds little beyond echoing the 'same niche' concept from the keyword parameter and does not explain the format or interaction of startDate or maxItems, so a 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 states a specific verb ('查询' / query), a specific resource (公众号爆款文章 / viral WeChat official-account articles), and a clear purpose (获取封面设计参考 / obtain cover-design references). It distinguishes this tool from WeChat search/write tools by focusing on cover design, though it does not explicitly name sibling alternatives.

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

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

The description implies when to use the tool: when the user needs cover-design reference from viral articles in the same niche ('同赛道爆款文章'). However, it gives no explicit guidance on when not to use it or which alternative tools to prefer, such as wechat-search or xiaohongshu-cover.

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 useful behavioral constraints—daily updates and the 30-day window—but it does not describe output ordering, result fields, or behavior for invalid dates. Since there is no output schema, this leaves some uncertainty about the returned 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?

A single compact sentence communicates the resource, the query method, update frequency, and time restriction with no filler. It is well-structured and 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?

For a low-complexity, one-parameter read-only ranking tool, the description plus schema is sufficient for an agent to know what to call and how to pass rankDate. Slightly more detail about the returned ranking fields would make it fully complete given the absence of an output schema.

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 documents the date format, the 30-day limit, and the yesterday/today aliases. The description only restates date-based lookup and the 30-day restriction, adding no new parameter meaning 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 names a specific resource—公众号阅读增长最快账号榜 (WeChat official account reading-growth ranking)—and a clear query mode (按日期查询). This distinguishes it from sibling tools like wechat-top-account and wechat-10w-hot, since it is specifically about accounts with the fastest reading growth.

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

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

The description gives clear usage context: query by date, updated daily, and only supports the last 30 days. It does not explicitly name alternatives or state when not to use the tool, so it stops short of a 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?

With no annotations provided, the description carries the full burden of behavioral disclosure. It does communicate a read-only intent through '查询' and '获取' and specifies the 10w+ article filter, which is useful. However, it does not disclose return format, ordering, pagination, or any limits, leaving meaningful behavioral aspects unaddressed.

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 that is easy to scan and front-loads the main purpose. There is mild redundancy between '查询' and '获取' and between '爆款' and '10w+', but the second clause does add the key filtering criteria, so the overall structure is acceptable.

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 output schema and no annotations, the description gives a reasonable high-level understanding but omits return value expectations, sorting, and result limits. The schema covers required parameters adequately, so invocation is possible, but an agent is left with uncertainty about what data will be returned and how it is structured.

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 the baseline is 3. The description adds only a general confirmation that results are filtered by category and time; it does not explain parameter purpose beyond what the input schema already states. The type parameter's allowed values remain vague ('等23个标准分类') in both the schema and the 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 a specific action—querying official-account original viral articles—and identifies the resource ('公众号原创爆款文章') plus the filtering dimensions (category and time). However, it does not differentiate this from the similarly named sibling 'wechat-10w-hot', which appears to target the same kind of data, so it stops short of a 5.

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 tells what the tool does but gives no explicit guidance on when to use it instead of sibling tools like 'wechat-10w-hot' or 'wechat-fastest-growing'. There is no mention of trade-offs, exclusions, or conditions that should route an agent to this tool 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 carries the full burden of behavioral disclosure. It conveys the core read-only behavior of checking content for sensitive expressions, but it does not disclose what the tool returns, whether it lists offending words, or any limitations such as false positives or coverage scope.

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 short and front-loaded with the core purpose. However, the second clause '检查文案中的敏感表述' partially restates the first clause, making it slightly redundant even though it adds a bit of nuance about sensitive expressions.

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?

There is no output schema and no explanation of what the tool returns, such as whether it returns a pass/fail result, a list of prohibited words, or a risk score. Since annotations are absent, the description needed to cover the return value expectations but did not, leaving the tool incomplete for an agent that must interpret results.

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 the parameter 'content' is already documented as '待检测文案内容'. The description adds only marginal context by calling the input '文案', which aligns with the schema but does not add new constraints like length limits, language, or formatting expectations.

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

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

The description states a specific verb and resource: '检测'/'检查' applied to '公众号违禁词' (WeChat official account prohibited words). It clearly distinguishes itself from sibling platform-specific tools like xiaohongshu-prohibited-word and douyin-prohibited-word by naming the 公众号 platform.

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

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

The usage context is implied through the platform name: use this tool for detecting prohibited words in WeChat official account copy. However, the description does not explicitly state when not to use it or mention alternatives such as douyin-prohibited-word or xiaohongshu-prohibited-word.

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 carries the full burden of behavioral disclosure. It states that the tool will inject WeChat-featured vocabulary and make sentences more vivid, attractive, interesting, and persuasive. However, it stays at a persona level and omits operational details like input handling, output format, or limitations.

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 flowery persona paragraph with noticeable redundancy: '具有硬核的公众号文案功底' and '需要具备精通语言的能力' overlap, and the same role/task framing is repeated. It front-loads the core idea but spends too many words restating it.

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 no-parameter generative tool, the description conveys the essential behavior and output style. However, it does not clarify how the source copy is provided or what the tool returns, which creates mild ambiguity given the empty schema and absence of an output schema.

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 zero parameters, so there is nothing for the description to add beyond the empty schema. Per the baseline for 0-parameter tools, this deserves a 4; there is no ambiguity or unmet need.

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 a specific action: transforming existing copy into high-readership WeChat official account copy with platform-specific stylistic traits. It implicitly distinguishes itself from siblings like wechat-write (new copy) and xiaohongshu-rewrite (different platform), though it does not name them explicitly.

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

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

The description implies the tool is for rewriting copy into WeChat viral style, but it provides no explicit when-to-use or when-not-to-use guidance, nor does it route to alternatives such as wechat-write or platform-specific rewriters. Usage is inferable but not directly stated.

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 behavioral disclosure burden. It only restates the search action and does not mention result ordering, pagination, rate limits, freshness, caching, or what qualifies as '爆款', leaving the tool's runtime behavior opaque.

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 filler and is easy to scan. It has slight redundancy because '公众号文章搜索' and '公众号爆款文章' overlap, but it remains efficient and front-loads the resource and action.

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 a simple input schema and no output schema or annotations, so the description should at least hint at the return value and behavior. It does not explain what the output looks like, what '爆款' means, or how maxItems and startDate affect results, leaving an important gap for the agent.

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 the input schema already documents keyword, maxItems, and startDate. The description adds minimal semantic context by mentioning '关键词' and '爆款文章', but it provides no extra detail about maxItems or startDate beyond what the schema already states.

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

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

The description states a clear action ('搜索') and resource ('公众号文章'), and narrows it to '爆款文章', so an agent can tell this is a keyword-based article search. It does not explicitly differentiate from sibling tools like wechat-10w-hot or wechat-original-hot, but the core purpose is still 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 phrase '按关键词搜索' implies the tool is for keyword-driven searches, which gives some usage direction. However, there is no explicit guidance on when to prefer this tool over sibling search or hot-list tools, and no alternatives or exclusions are mentioned.

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