SocialDataX 好看视频 Haokan MCP

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that pagination is supported and where comment_id originates, which is helpful, but gives no auth requirements, rate limits, or pagination termination behavior beyond what the schema already states.

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 compact two-clause sentence that front-loads the core action, then appends the prerequisite and the sibling alternative. No filler; every clause carries 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?

With an output schema present, return values need not be described, and annotations cover the read-only/open-world nature. The description covers the key prerequisite and the alternative tool, leaving only minor gaps (e.g., behavior on invalid or deleted comment IDs).

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 url, comment_id and page_token in detail. The description only restates the comment_id provenance (already in the schema) and adds no new syntax or format guidance, 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?

States a specific verb+resource: reading the full reply list for a first-level comment, given a video page URL and comment ID, with pagination noted. It explicitly names the sibling entry point (haokan_get_comment_replies_by_video_id), so an agent can distinguish it without opening either schema.

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 the prerequisite for comment_id (taken from the video comment list) and names the alternative entry point. However it does not spell out the selection condition in words (use this when you have a URL, the other when you have a video ID) – that is left to inference from the names.

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 already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds the pagination behavior, but that is largely restated by the page_token schema field, and no other behavioral context (rate limits, ordering) is added.

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 that identifies the action and resource immediately, followed by the routing clause. The trailing semicolon clause is dense but each part carries 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?

An output schema exists, so return values need not be explained. The description covers pagination and ID sourcing for a moderate three-parameter read tool; only the reply ordering or depth semantics are left implicit.

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 each parameter already documented in detail, so the baseline is 3. The description reinforces where comment_id and video_id originate but adds no syntax or format 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?

States a specific verb (读取/read), resource (完整回复列表/full reply list), and scope (按视频 ID和一级评论 ID), and explicitly names the sibling it is the alternate entry point to (haokan_get_comment_replies_by_url). An agent can distinguish this from by_url without opening either schema.

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 routes the agent: comment_id comes from the video comment list, and the alternative entry point is named as haokan_get_comment_replies_by_url. It stops short of stating the condition that selects one over the other beyond ID availability.

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 already declare readOnlyHint=true and openWorldHint=true, so the safety posture is covered. The description adds genuine behavioral detail beyond them: results reflect currently trending terms (freshness) and the endpoint is non-paginated, which the agent could not infer from the empty schema.

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

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

A single compact sentence that leads with the payload returned and immediately follows with the two scope limits. No filler, no redundancy; every clause carries information an agent needs.

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?

Output schema exists, so return-value structure need not be described, and there are no parameters to document. The description supplies what the structured fields cannot: what is returned (terms + heat) and the two hard limits (no video list, no pagination).

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

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

The tool takes zero parameters, so there is no parameter semantics to explain; schema coverage is 100% and the schema is an empty object. Baseline 4 applies, with no misleading parameter claims in the 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?

States a specific verb+resource: fetching Haokan Video's current hot search terms and their heat values. It also pre-empts confusion with the video-list siblings by explicitly saying it does not return a popular video list, though it names no sibling tool directly.

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?

Gives two concrete exclusions that steer correct use: no hot video list and no pagination support, which tells the agent this is a single-shot keyword endpoint. It stops short of naming a preferred alternative for video lists (e.g. haokan_search_videos), so it is guidance-by-exclusion rather than full when-to-use 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds one useful boundary disclosure ('不返回作品列表' – does not return posted videos), but no auth, rate-limit, or pagination context. Modest value beyond annotations earns a 3.

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 sentence with the purpose front-loaded, followed by the alternative routing rule and the scope boundary. Every clause earns its place with zero 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?

An output schema exists, so return values need no prose. Purpose, alternative-tool routing, and the works-list exclusion are all covered; nothing an agent needs to call this correctly is missing.

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

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

Schema description coverage is 100% and the schema itself details the required URL format plus where to obtain it (search results, video detail, comment author profile_url). The description adds nothing beyond that, 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?

States a specific verb (获取/retrieve) and resource (好看视频用户资料/user profile) scoped by input type (按用户主页链接/by homepage URL). It explicitly distinguishes itself from the sibling haokan_get_user_info_by_user_id, so an agent can route without opening either schema.

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?

Names the alternative (haokan_get_user_info_by_user_id) and the exact condition that selects it (只有用户 ID 时/when only a user ID is available). The boundary note about not returning the works list further separates it from haokan_get_user_posted_videos_by_profile_url.

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 already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuine extra scope context with '不返回作品列表', telling the agent this fetch excludes the video list. It stops short of return-format or pagination detail, but that is largely covered by the output schema.

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

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

A single semicolon-delimited sentence that front-loads the core purpose, then adds sourcing, the alternative route, and the scope exclusion in priority order. Every clause earns its place with zero 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?

With a 100%-covered schema for the single parameter and a declared output schema, the only remaining burdens are routing and scope — both addressed. The agent has everything needed to select between the ID and URL variants and call correctly.

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

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

Schema description coverage is 100%, so baseline is 3: the schema already documents the user_id pattern, sourcing options, and the non-empty constraint. The description's note about sourcing the ID from search results largely repeats what the schema already states, adding no new syntax or format meaning.

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

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

States a specific verb (获取) and resource (好看视频用户资料) scoped by user ID, and explicitly distinguishes itself from the sibling haokan_get_user_info_by_url. The trailing '不返回作品列表' further sharpens what this tool is not.

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?

Says the ID comes from user search results and names the exact alternative (haokan_get_user_info_by_url) plus the condition that selects it (holding a profile link). Both the when and the when-not are present with no inference required.

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 already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds the useful behavioral note that results are paginated, plus the input-shape constraint that only profile URLs (not video links) are accepted. It stops short of describing return structure, but an output schema exists to carry that.

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 tight sentence with semicolon-separated clauses: purpose first, then the two routing constraints. Zero waste, nothing buried.

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-only paginated list tool, the description handles purpose, routing, the two exclusions, and pagination support, while annotations cover the safety profile and an output schema covers return values. Nothing an agent needs to call it correctly is missing.

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 both parameters (profile_url and page_token) are already fully documented in the schema, including the source of profile_url and the same-user rule for pagination. The description adds no syntax or format detail beyond that, 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?

States a specific verb and resource (get the list of videos a Haokan user has posted), scoped by the keying method (profile URL), and names the sibling it is distinct from (haokan_get_user_posted_videos_by_user_id). An agent can distinguish it from every sibling without opening the schema.

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

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

Explicitly gives a negative condition (do not pass a video link) and an alternative with its selecting condition (if you already have a user ID, use haokan_get_user_posted_videos_by_user_id). Both when-to-use and when-not-to-use are covered.

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 already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds that results are paginated, but the schema's page_token and the output's next_page_token already convey this, so the added behavioral value is modest.

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

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

Two short clauses, zero filler, with the tool's scope front-loaded and the routing hint second. 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?

With a full input schema, an output schema, and annotations, the description covers purpose, ID source relationship, and alternative routing adequately. It omits nothing critical, though it says nothing about the expected result shape or any access constraints.

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 user_id sourcing and page_token continuation semantics are fully documented in the schema itself. The description adds no parameter-level meaning beyond what is already there; 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?

States a specific verb and resource ('获取用户发布视频列表') scoped by the identifier ('按用户 ID'), which immediately distinguishes it from the profile_url sibling. An agent can pick this tool without opening the schema.

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

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

Explicitly names the alternative (haokan_get_user_posted_videos_by_profile_url) and the exact condition that selects it ('持有用户主页链接时'). This is a textbook when/when-not routing statement.

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?

Beyond readOnlyHint/openWorldHint, it discloses two behavioral traits that matter: results are paginated, and any attached replies are only previews (not full reply data). It does not mention rate limits or auth, but the pagination and reply-preview semantics are the key operational facts.

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 tight clauses: scope/pagination/preview first, then the alternative-tool pointer. No filler, front-loaded, and every clause carries actionable 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?

An output schema exists so return values need no explanation; the description supplies the remaining essentials — pagination behavior, preview-only replies, and the by_video_id alternative. Only minor gaps (e.g. what determines a valid URL, reply-tool routing) remain.

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 both parameters (url, page_token) are documented in the schema, including the next_page_token round-trip. The description only echoes that pagination is supported, adding no syntax or format detail beyond the schema, so 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?

Specific verb+resource: reads Haokan video first-level comments from a page URL. It scopes the result (first-level only, replies are preview only) and explicitly names the sibling that handles the other input form, haokan_get_video_comments_by_video_id.

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

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

It states the input-context condition clearly: use this when you have a page link, and use haokan_get_video_comments_by_video_id for the other input. It lacks explicit when-not-to-use guidance (e.g. whether replies require the dedicated replies tool), but the routing is mostly 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 readOnlyHint and openWorldHint already covering the safety profile, the description still adds real behavior: results are paginated, only top-level comments are returned, and attached replies are preview-only (partial data). That preview caveat is valuable context an agent would otherwise miss.

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

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

Three short clauses, front-loaded with the core action and scope; the routing note is placed last. Compact and waste-free, though slightly terse.

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?

An output schema exists, so return values need no explanation here. The description covers scope, pagination, the reply-preview limitation, and the sibling route — enough for correct invocation, with only minor room for more depth.

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 both video_id and page_token are already fully documented in the schema, including the ID format and the next_page_token continuation contract. The description adds no parameter-level detail beyond that, 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?

States a specific verb+resource: reads top-level (一级) comments for a Haokan video identified by video ID, with pagination support. It explicitly distinguishes itself from the URL-based sibling, so an agent can route correctly without opening either schema.

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?

Names the alternative explicitly — '另一种输入使用 haokan_get_video_comments_by_url' — giving a clear rule: use this tool when the input is a video ID. It stops short of stating exclusions or level-of-comment conditions, but the routing guidance is concrete.

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 already declare readOnlyHint=true and openWorldHint=true, so safety and network behavior are covered structurally. The description adds a genuinely useful operational caveat that annotations do not convey — the playback URL may expire ('播放地址可能过期'). It stops short of describing pagination or freshness of the author summary, but the expiry warning is real added value.

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 front-loads the purpose, then the alternative route, then the expiry 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?

An output schema exists, so return-value documentation is not the description's burden. With purpose, sibling routing, the expiry warning, and full schema coverage of the sole parameter, an agent has everything needed to invoke this correctly.

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

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

Schema description coverage is 100% for the single url parameter, and the schema itself spells out the required format (https://haokan.baidu.com/v?vid=数字ID, obtainable from search results' share_url). The description only restates that input comes from a page link, adding no syntax or format detail beyond the schema, 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?

Names a specific verb and resource ('读取好看视频详情、播放地址和作者摘要' — read Haokan video detail, playback URL, author summary), which is more specific than the title/name alone. It also explicitly distinguishes itself from the sibling haokan_get_video_detail_by_video_id, so an agent can route between the two without opening either schema.

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

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

States the routing condition explicitly: use this tool when you have a page link, and use haokan_get_video_detail_by_video_id when you only have a video ID. That is a clear when/when-not with a named alternative, leaving nothing 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so safety is covered. The description adds genuinely new behavioral context beyond them: the playback address may expire (时效性 caveat) and it enumerates the returned payload. It does not cover failure modes for an invalid/nonexistent ID, but that is a modest gap for a read-only tool.

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

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

Three tightly packed clauses with zero filler: purpose first, sibling routing second, freshness caveat last. Front-loaded and free of restatement of the name.

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, fully documented read with an output schema and read-only annotations, the description supplies everything needed: what it returns, when to prefer the URL sibling, and the expiration caveat. Nothing an agent needs to call it correctly is missing, though it could note behavior on a stale/unknown ID.

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 video_id parameter already documents the numeric-string format, an example value, and where to obtain it (search results). The description adds no syntax or format detail beyond that, 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?

States a specific verb and resource (read Haokan video detail by video ID) plus the payload it returns (播放地址, 作者摘要), and explicitly distinguishes itself from the sibling haokan_get_video_detail_by_url. An agent can route between the two ID/URL variants without opening either schema.

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?

Gives an explicit selection rule: use this tool when you hold a video ID; use haokan_get_video_detail_by_url when you hold a page link. The alternative is named and the condition that selects it is stated, leaving nothing 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?

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds useful behavioral boundaries beyond them: no video/user payloads and no pagination support, which tells the agent not to attempt paging. It does not need to describe returns since an output schema exists.

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 tight sentence with three clauses, front-loaded with verb and resource, then scope limits. Every clause carries distinct information (purpose, use case, exclusions) and there is no filler.

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

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

For a single-parameter, read-only suggestion endpoint with an output schema, the description supplies everything an agent needs: purpose, intended use, and the two boundaries (no content results, no pagination) that most affect 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?

There is a single parameter with 100% schema description coverage, so the schema already explains 'keyword' and even warns against links/pagination tokens. The description adds no parameter-level detail beyond what the structured data provides, which is the expected 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?

States a specific verb and resource ('获取好看视频搜索联想词') and immediately delimits scope with what it does not return (videos or users), which cleanly separates it from siblings haokan_search_videos and haokan_search_users. An agent can pick this tool without opening any schema.

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?

Gives a clear use case ('用于补全或扩展关键词') and implicitly routes away from content-search tools by stating it returns no video/user results. It stops short of naming the alternative tools or the condition for preferring this one over them, so it is clear but not fully explicit.

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

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

Annotations already declare readOnlyHint and openWorldHint, and the description adds useful behavior beyond that: it returns user summaries and supports pagination. It does not mention rate limits or result-size behavior, but with the safety profile covered by annotations the remaining addition is meaningful.

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 front-loads the primary purpose and appends the exclusion clause. 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?

With an output schema present, return values need no elaboration, and annotations cover the safety profile. The description supplies the purpose, scope, return type, pagination support, and the key exclusion, which is everything an agent needs to select and invoke it correctly among the numerous siblings.

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 keyword and page_token semantics (including the 'do not modify/truncate/generate' constraint) fully documented in the schema. The description adds no parameter-level detail beyond what the schema already provides, 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?

States a specific verb (搜索) and resource (好看视频用户、账号或创作者), and explicitly negates the adjacent resource (不用于搜索视频), which cleanly distinguishes it from the sibling haokan_search_videos. It also states what is returned (用户摘要) and that pagination is supported.

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 exclusion "不用于搜索视频" gives a clear when-not and routes the agent toward the video-search sibling without naming it. No explicit prerequisites or named alternative tool, so it falls short of a full 5.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds useful behavioral context beyond that: results are video summaries and the tool supports pagination. It does not mention rate limits or result-count behavior, so it stops short of a 5.

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 tightly packed sentence: purpose first, then return/pagination behavior, then the exclusion clause. Every clause earns its place with no filler.

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

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

An output schema exists, so return values need not be described in prose. With safety covered by annotations, full schema coverage, and explicit scope plus exclusions, an agent has everything needed to invoke this correctly.

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

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

Schema description coverage is 100%, so the schema already fully documents keyword and page_token, including the warning not to pass URLs or tokens. The description adds nothing parameter-specific, 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?

States a specific verb+resource (按关键词搜索好看视频) plus what it returns (视频摘要) and its pagination scope. It also explicitly carves out what it is not for, distinguishing it from haokan_get_video_detail_by_url and haokan_search_users without the agent needing to open either schema.

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?

Gives explicit when-to-use (查找视频) and when-not-to-use (读取指定视频链接的详情, 查找用户), which routes the agent to the detail-by-URL and user-search siblings. Nothing about 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?

Annotations already declare readOnlyHint=true, and the description reinforces that this is a read-only balance query. It adds useful context by tying the balance to the current API Key and pointing to the billing dashboard for recharges. No contradictions or hidden side effects are indicated.

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

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

The description is two short sentences: the first states the core purpose, and the second provides an actionable billing link. Every word earns its place without unnecessary 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?

For a zero-parameter, read-only balance query with an output schema, annotations, and a billing link, the description is fully sufficient. No additional information is needed for an agent to select and invoke it correctly.

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

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

The tool has zero parameters Belarusand schema coverage is 100%, so parameter semantics are not a burden on the description. The description still adds value by explaining what the returned balance represents.

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 (query) and resource (current API Key account's SocialDataX points balance), including Chinese and English terms. It is unambiguous and obviously distinct from the YouTube-focused 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 identifies the exact context: querying the balance for the current API Key accounttons. It also provides a relevant follow-up URL for recharging. There are no competing sibling tools for balance checking, so no explicit alternatives are needed.

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