SocialDataX 微信 WeChat MCP

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.

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

The description adds a valuable behavioral limitation not present in annotations: '当前不支持翻页' (currently does not support pagination). The readOnlyHint annotation already indicates a safe read operation, and the description is consistent with it. No contradiction detected.

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

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

The description is a single, front-loaded sentence that states the core purpose and a key limitation. Every word earns its place, with 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?

This is a simple, no-parameter tool with an output schema available. The description covers what it does and a key limitation, and the output schema handles return values. No significant gaps 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?

The tool has zero parameters and the schema is empty, so schema coverage is trivially 100%. The baseline for 0-parameter tools is 4, and the description does not need to add parameter semantics. No gaps exist.

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

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

The description clearly states the tool retrieves the WeChat Channels hot list ('获取微信视频号热榜'), using a specific verb and resource. It distinguishes itself from siblings like wechat_search_videos and wechat_get_video_detail_by_url by being the only one focused on the hot list.

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

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

The description implies usage for retrieving the hot list, but does not explicitly state when to use this tool versus alternatives or provide exclusion criteria. There is no mention of alternatives or scenarios where other tools would be more appropriate.

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 description adds nothing beyond that. It doesn't describe pagination behavior, ordering, or any side effects. With annotations covering the safety profile, the description's minimal addition is acceptable but not enriching.

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 that is direct and free of fluff. The purpose is front-loaded and nothing is redundant.

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 read-only list tool with an output schema and fully documented parameters, the description is sufficient. It covers the core action. Slight gap: it doesn't mention that the page_token is used for continued pagination, but that's already in the schema. Overall, the combination of schema and description is complete enough for an agent to 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 both parameters (account_id and page_token) are fully documented in the schema. The description doesn't add any semantic detail beyond the schema, such as the meaning of the account_id format or the pagination rule, which are already in the schema. 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 clearly states the verb (获取/get) and the resource (文章列表/article list) with a specific scope (按公众号账号 ID/by account ID). It distinguishes from siblings like wechat_get_mp_account_info_by_account_id which retrieves account info, not articles.

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: when you have an account ID and need its articles. However, it doesn't explicitly state when to prefer this over siblings or mention any exclusions (e.g., if you have a URL, use wechat_get_mp_article_detail_by_url). It provides no context about the pagination flow beyond what the schema explains.

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 agent knows this is a safe read operation. The description adds no additional behavioral context (e.g., authentication needs, rate limits, output behavior), but it does not contradict the annotations.

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

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

The description is a single, concise sentence with no wasted words. It is appropriately sized for a simple one-parameter read-only tool, though it lacks the comparative structure seen in higher-scoring examples.

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

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

Given the tool's low complexity, full schema coverage, and existing output schema, the description provides enough for basic invocation. However, it lacks explicit usage guidance and does not address when to prefer this tool over siblings, leaving an agent to rely on name inference.

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 parameter description already explains semantics with an example format (gh_114e76fd6e5d). The tool description adds nothing beyond the schema, so the baseline score of 3 applies.

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

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

The description '根据公众号账号 ID 获取账号资料' clearly specifies the action (获取/get) and resource (账号资料/account info), and the tool name disambiguates it from siblings like wechat_get_mp_account_articles_by_account_id. However, the description itself does not explicitly differentiate from similar tools, only the name 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?

There is no guidance on when to use this tool versus alternatives. The schema description mentions using account_id from article details, but that is parameter sourcing, not tool selection context. No exclusions or conditions are provided to help an agent choose this tool over siblings such as wechat_get_mp_account_articles_by_account_id.

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, covering the safety profile. The description adds the notable behavioral trait that omitting comment_id triggers automatic selection of a comment that has replies, which is genuine value beyond annotations, but it says nothing about pagination behavior or return limits.

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

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

A single compact sentence that front-loads the core action (fetch comment replies by article URL) followed by the key conditional parameter behavior. 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?

With an output schema present and 100% schema coverage plus annotations covering safety, the description need not explain return values or pagination detail. It is complete enough for correct invocation, missing only explicit sibling routing.

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 url, comment_id, and page_token are fully documented in the schema (including the pagination-chain constraint and 'do not pass reply IDs'). The description only restates the comment_id auto-select behavior, so it adds little beyond the schema; 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+resource combination ('获取评论回复' by article URL) and clarifies the input accepts either a link or share text. It is distinguishable from the sibling wechat_get_mp_article_comments_by_url because it targets replies rather than first-level comments, though it never names that sibling 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 explains the conditional behavior of comment_id (pass it to target a reply-bearing comment, omit it and the service auto-selects one), which is useful invocation guidance. It does not state when to prefer this tool over wechat_get_mp_article_comments_by_url or wechat_get_video_comment_replies_by_comment_id, so usage is only implied.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the tool is known to be read-only. The description adds no further behavioral context, such as what specific stats are returned or any caveats about invalid URLs. It does not contradict annotations, but adds minimal value beyond them.

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

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

The description is a single sentence that is directly to the point, with no filler or redundancy. It is efficiently front-loaded with the core purpose.

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

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

With only one parameter, an output schema present, and annotations covering read-only behavior, the description is largely sufficient for an agent to call the tool correctly. The only minor gap is the lack of specificity about what 'interaction statistics' includes, but this is 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 description coverage is 100%, and the parameter 'url' is already well documented with an explanation and example. The tool description does not add any additional meaning about the parameter, 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 ('获取' / get), resource ('公众号文章' / WeChat Official Account article), and outcome ('互动统计' / interaction statistics). It clearly distinguishes this from sibling tools like comments, detail, or user info, since it focuses on statistics rather than content or user data.

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

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

There is no explicit guidance on when to use this tool versus alternatives. The description implies it is for retrieving interaction statistics, but it does not mention exclusions or point to siblings like get_mp_article_detail for content or get_mp_article_comments for comments.

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 include readOnlyHint: true, which already indicates a safe read operation. The description adds the behavioral detail that the tool parses the author from the URL or share text before fetching user info, and that it supports both video and graphic links. This adds value beyond the annotations, though it does not disclose potential failure modes or rate limits, keeping it at a 4 rather than 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?

The description is a single, concise sentence that is front-loaded with the core purpose and directly states the input type and outcome. There is zero redundancy or wasted wording; every phrase adds value.

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

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

Given the tool's simplicity (one parameter), the presence of an output schema, and annotations that declare read-only and open-world behavior, the description is fully sufficient. It explains what the tool does, how it works (parsing), and the input format. No additional details are required.

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

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

The input schema already provides a comprehensive description of the 'url' parameter (including examples and acceptable formats) with 100% coverage. The description adds no additional parameter semantics beyond restating that the tool parses the author, which is not needed given the schema's detail. Baseline 3 is correct when the schema carries the parameter documentation burden.

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

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

The description clearly states the tool's function: given a WeChat Channels video/post link or shared text, it parses the author and retrieves user information. It uses a specific verb (获取) and resource (用户信息), and distinguishes from sibling tools like wechat_get_user_info_by_user_id by explicitly mentioning the URL-based approach.

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 on when to use this tool (when you have a work link or share text), but it does not explicitly mention alternatives or exclusions. The sibling tools suggest there is a by-user-id variant, but the description does not state to use that when a user ID is available. This is implied but not stated, so a 4 is appropriate.

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 adds no further behavioral context (rate limits, auth, data freshness, or meaning of openWorldHint). It simply restates the purpose without any extra disclosure, so it adds little beyond the annotation.

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 sentence that directly states purpose and usage condition with no filler. Efficient and front-loaded, ideal for a simple tool.

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

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

For a 1-parameter read-only tool with an output schema, the description combined with the schema covers essentials. Missing explicit error handling and a direct pointer to the URL-based sibling, but those are inferable from the sibling names and schema guardrails.

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

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

The schema description for user_id is thorough, covering format, sourcing, and negative conditions. With 100% schema coverage, the tool description needs to add nothing extra, 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?

States a specific verb and resource: 'get user info' by WeChat Channels user ID. Clearly distinguishes from URL-based sibling (wechat_get_user_info_by_url) and from video-listing tools by explicitly naming the lookup key.

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 says to use directly when the user provided a valid user_id, and the schema description elaborates where to source the ID otherwise and enforces the v2_...@finder format. It provides a clear condition but stops short of explicitly naming alternatives like the URL-based 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety and world-model. The description adds meaningful behavioral context: it parses the author from the link, returns both video and image-text content, and supports page_token pagination. No contradiction with annotations.

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

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

A single, dense sentence that front-loads the purpose (parse author, get list) and ends with the pagination capability. Every phrase earns its place with no waste, and it is appropriately structured for quick comprehension.

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 paginated list-retrieval tool with a read-only, open-world profile and a full input schema plus output schema, the description covers the core behavior, output scope, and pagination. It does not explicitly route to the sibling user_id tool, but the name and context make that inferable, so no critical gap exists.

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 url and page_token already well-documented. The description restates the URL flexibility (video/image-text/share text) and pagination but adds no new meaning beyond what the schema provides. Baseline 3 is appropriate given high 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 clearly states a specific action: parse the author from a WeChat Channels work link or share text, then retrieve the user's published works list (videos and image-text). It distinguishes itself from siblings like wechat_get_user_posted_videos_by_user_id by specifying the input is a URL, making the resource and 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 clearly implies when to use this tool: when you have a work link or share text, as it says '根据...链接...解析作者'. However, it does not explicitly name alternative tools (e.g., the user_id variant) or state exclusions, so it falls short of the 'explicit when/when-not' bar but provides clear context.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering the safety profile. The description adds modest context about result content and pagination, but does not go meaningfully beyond the schema for page_token semantics. No contradiction with annotations.

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

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

One compact sentence with the core operation front-loaded, followed only by essential operational facts: when to use it and pagination support. There is no filler or redundant elaboration.

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 two-parameter read-only list tool with a rich input schema and an output schema, the description is complete. It states purpose, usage condition, and pagination, while the structured fields cover the remaining invocation details.

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 parameter descriptions are highly detailed, covering user_id format/sources and exact page_token reuse rules. The main description adds little 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?

The description clearly states the operation: fetch a WeChat Channels user's published works list by user ID, and notes that the list includes videos and image-text posts. The by_user_id framing plus the explicit '根据微信视频号用户 ID' makes it distinguishable from the sibling by_url tool.

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

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

It provides a clear usage condition: use directly when a valid user_id is already available, and support for page_token pagination is stated. It does not explicitly name exclusions or the by_url alternative, but the context is clear enough for tool selection.

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 valuable behavioral context: the requirement that object_id and object_nonce_id must come from the same video and be passed together, and the rationale for obtaining missing IDs via other tools. There is no contradiction with annotations.

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

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

The description is somewhat long but efficiently packed with actionable guidance. It opens with the core purpose, then provides structured usage scenarios. No filler sentences; every clause contributes to correct tool invocation.

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

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

Given the presence of an output schema, the description doesn't need to explain return formats. It covers when to use, how to handle missing inputs, and usage constraints. The pagination mechanism is described in the page_token parameter. A minor gap is the lack of explicit mention of rate limits or error handling, but these are not critical 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% with detailed parameter descriptions including examples. The description adds workflow-level semantics: emphasizing same-video pairing of object_id and object_nonce_id, insisting comment_id be a top-level comment (not a reply), and detailing page_token reuse across pages. This goes beyond the schema's basic definitions.

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

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

The description clearly states the tool's function: retrieving comment replies for a specific video based on object_id, object_nonce_id, and comment_id. It distinguishes itself from sibling tools like wechat_get_video_comments_by_object_id (which fetches top-level comments) by focusing on replies, making the purpose unambiguous.

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

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

The description provides explicit when-to-use guidance: use directly when full ID combos are provided; call other tools to complete missing IDs when partial info exists; ask user for video location info when absent. It also explicitly warns not to pass a reply's comment_id, preventing a common misuse.

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, covering the non-mutating nature and external-world interactions. The description does not contradict these annotations and adds minor context about how to obtain the IDs, but it does not disclose additional behaviors such as rate limits, error handling, or exactly what happens on invalid IDs. Given annotation coverage, this level is acceptable.

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 efficiently conveys the purpose and usage constraints without redundancy. It is front-loaded with the main condition (having the IDs) and then provides actionable routing guidance, maintaining good structure despite being compact.

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

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

Given the tool's simplicity (comment list retrieval with pagination), the description adequately covers the primary scenario and input requirements. Output schema handles return values, and page_token pagination is documented in the schema. The description also addresses how to obtain IDs when not supplied, making it reasonably complete for an agent to 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 each parameter is already documented. The description adds meaningful value by stating that object_id and object_nonce_id must be passed together and unchanged, and by guiding the agent on where to acquire them if not initially provided. This goes beyond bare schema definitions and clarifies the relationship between the two required 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 states a specific operation — fetching the comment list for a given video — and explicitly names the required identifiers (object_id and object_nonce_id). It clearly differentiates itself from sibling tools like wechat_get_video_comments_by_url (which uses a URL) and wechat_get_video_comment_replies_by_comment_id (which handles replies), so an agent can distinguish it without inspecting schemas.

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 object_id and object_nonce_id are already available) and provides fallback sources for obtaining them (from detail or first-level comment results). It also tells the agent to call the detail tool first when only an encrypted_object_id is present, effectively excluding the wrong paths and routing to the correct sibling.

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, covering the safety profile. The description adds no extra behavioral context (e.g., pagination handling, rate limits, or what happens with invalid URLs). Since annotations carry the safety burden and the description does not contradict them, a neutral score is appropriate.

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, direct sentence states the core purpose with no filler. It is front-loaded with the key verb and resource, making it easy to parse quickly. Every word contributes to understanding.

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 list operation with two parameters, both of which are fully documented in the schema, the description is sufficiently complete. An output schema exists for return values, so the description doesn't need to explain them. The only minor gap is not explicitly noting that the tool is read-only, but that is already in annotations, so the omission is forgiven.

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%, with detailed descriptions for both 'url' and 'page_token'. The description essentially repeats the URL flexibility (link or shared text) already present in the schema, adding little beyond what structured data provides. The page_token field is not mentioned in the description, but the schema fully explains its pagination semantics, so no loss occurs.

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 action (获取评论列表) and the resource (微信视频号视频链接或包含链接的分享文案). It distinguishes itself from sibling tools like wechat_get_video_comments_by_object_id by specifying the URL-based input, giving agents a precise way to select this tool.

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 specifies the input condition (URL or shared text) but does not explicitly mention when to avoid this tool or point to alternatives such as the object-ID-based sibling. Usage is implied rather than explicitly contrasted with similar tools, so agents must infer which tool to pick based on input type without clear 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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the read-only nature is covered. The description adds only the requirement that the ID be '合法' (valid), which is a slight behavioral hint, but it provides no further details on side effects or response characteristics. No contradiction with annotations is present.

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

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

The description is a single sentence that front-loads the core action ('获取视频详情') and then provides needed sourcing guidance. There is no filler; each clause serves a purpose, making it both concise and well-structured.

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

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

For a one-parameter read-only tool with an output schema and annotations covering safety, the description is adequate: it states the operation, explains how to obtain the required ID, and the output schema handles return values. The only minor shortfall is not routing explicitly to the by-URL sibling, but that is not essential for correct invocation of this tool.

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

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

Schema description coverage is 100% and the description's parameter note is essentially the same as the schema's. The practical guidance about sourcing the ID from search or author list is repeated from the schema, so no new semantic information is added. Baseline 3 is appropriate given 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?

The description clearly states the tool's purpose: fetching video details based on a valid encrypted_object_id. It differentiates from siblings by specifying the identifier type ('encrypted_object_id') rather than a URL or user ID, but it does not explicitly name the by-URL sibling 'wechat_get_video_detail_by_url'.

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 a concrete usage condition: when the user has already provided the encrypted_object_id, use it directly; otherwise obtain it from wechat_search_videos or the author's video list. This is actionable context, but it stops short of explicitly stating when to use the alternative by-URL tool or other 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?

Annotations (readOnlyHint=true, openWorldHint=true) already establish this as a safe, environment-dependent read operation, and the description is consistent with them. The description adds a mild behavioral nuance—it accepts share text and extracts the link—but adds no context on return shape parsing, error cases, or rate limits. No contradiction with annotations.

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

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

A single, tightly written sentence that front-loads the resource (WeChat Channels work), then the input forms, then the action. No filler words, and the sentence order matches how an agent would think about invoking 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?

The tool is simple (1 param, output schema present, read-only annotations), and the description covers the input essential. The clear gap is routing context: with siblings like wechat_get_video_detail_by_encrypted_object_id and wechat_get_video_comments_by_url in the same family, the description does not help the agent decide between them, relying entirely on tool-name intuition.

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 single 'url' parameter is already well documented with examples (raw link and share text containing the link). The description essentially restates the schema's parameter documentation rather than adding new meaning, 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: '获取作品详情' (get work detail) for WeChat Channels, and specifies the input form (video/image-text link or share text containing a link). This is clear, but it does not explicitly contrast with the sibling wechat_get_video_detail_by_encrypted_object_id; differentiation relies on the tool name's 'by_url' suffix rather than an explicit statement.

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 context is implied: when the agent has a link or share text and wants work details, this tool applies. However, there is no explicit when/when-not guidance or mention of the natural alternative (wechat_get_video_detail_by_encrypted_object_id), leaving the agent to infer routing from naming conventions.

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 mark the tool as readOnly and openWorld, so the description's main contribution is the explicit constraint that only numeric object_id is accepted, plus the schema's note to avoid encrypted_object_id or video links. This adds practical behavioral context beyond the annotations. However, it does not disclose potential error conditions or response nuances, but given the annotations cover safety, this is acceptable.

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

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

The description is extremely concise – two short sentences. It front-loads the primary purpose and then states the key constraint. There is no redundancy or filler. Every word contributes to understanding the tool's core function and limitation.

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 an output schema, the description covers the essential purpose and the one critical input restriction. It does not explicitly describe the return format, but the presence of an output schema mitigates that gap. Given the tool's simplicity, the description is reasonably complete, though it could mention whether the share link is a full URL or relative path.

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

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

The input schema already documents the parameter with an example and a caution against passing encrypted IDs or links, giving 100% coverage. The description adds the additional constraint that the object_id must be numeric, which is not present in the schema description. This extra clarity nudges the score above the baseline of 3, though the addition is minor.

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 action ('获取分享链接' – get share link) and the resource ('微信视频号作品 object_id' – WeChat Channels work object_id), making the purpose specific. It does not explicitly differentiate from sibling tools like wechat_get_video_detail_by_object_id or wechat_get_video_comments_by_object_id, but the verb 'get share link' is unambiguous enough that an agent can infer its distinct role.

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 such as wechat_get_video_detail_by_url or wechat_get_video_comments_by_object_id. It only states a constraint ('只接受数值 object_id') but does not explain scenarios or trade-offs. An agent must rely on the tool name and schema alone to decide, which is insufficient for a family of similar video 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?

Annotations already declare readOnlyHint: true, but the description adds valuable context: it waits up to 240 seconds per call and does not create new tasks or trigger reprocessing. This aligns with the read-only annotation and adds specifics about the tool's behavior that the agent needs to know, such as the maximum wait time. No contradiction is present.

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, focused sentence that front-loads the core action (querying status) and then adds the key constraints (240-second wait, no task creation) without any redundancy. It is efficient and well-structured, with no wasted words.

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

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

Given the tool's simplicity (one parameter), the presence of a detailed schema for that parameter, and annotations covering read-only behavior, the description is complete enough for an agent to call it correctly. It covers what it does, how to get the job_id, and what it doesn't do. The only minor gap is a lack of information about expected response format or failure handling, but since an output schema exists, this is not critical.

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 for the single parameter 'job_id' with a detailed description including instructions and exclusions. The tool description adds no additional parameter-specific information beyond what the schema already provides, so the baseline of 3 is appropriate—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 clearly states the tool's purpose: querying the status of a WeChat video speech-to-text task using a job_id. It explicitly distinguishes this from the submit tools by mentioning 'submit 工具返回的 job_id', making the specific resource and action unambiguous. The verb '查询' (query) and the resource '任务状态' are precise, and the sibling comparison is clear.

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 guidance on how to obtain the job_id (user-provided or from submit tools) and what not to pass (encrypted_object_id, object_id, or video links). It also states that no new tasks are created. However, it does not explicitly contrast with alternatives (e.g., 'use this after submitting a job and when polling'), but the context and the mention of submit tools imply the intended usage, so this is clear but could be more 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, so the safety profile is covered. The description adds real behavioral context beyond that: it discloses pagination via page_token and that the returned user_id is the handoff key for the profile and posted-videos tools, which helps chain calls. It does not mention rate limits or quota costs, 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?

The content is front-loaded with the primary purpose and the routing guidance is compactly appended with no filler sentences. It is slightly dense with three distinct ideas (search scope, pagination, downstream tooling) in one block, but every 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?

With an output schema present, return-value documentation is not needed, and the description still covers the essentials: search scope, the pagination parameter's role, what the returned user_id is for, and which sibling to use when the ID is already known. 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%, so both keyword and page_token are already documented in the schema (including the 'leave empty first time, reuse next_page_token with unchanged keyword' rule). The description's mention of page_token pagination adds framing but no syntax or constraints 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?

The description states a specific verb and resource (查找微信视频号用户) plus the two supported lookup modes (keyword or 视频号 ID), which immediately separates it from siblings like wechat_search_videos and wechat_search_mp_articles. It also states what is out of scope (微信联系人和公众号), so an agent can disambiguate 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?

It explicitly routes the agent: when a user_id or 作品链接 is already available, use the user-profile tool instead of this search, and it explicitly excludes contact and official-account search. That is a clear when-to-use, when-not-to-use, and named-alternative 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?

Annotations already signal readOnlyHint and openWorldHint; the description adds meaningful scope behavior: it currently returns videos but not image-text posts, and supports pagination via page_token. It does not go into rate limits or failure modes, but for a read-only search tool this is adequate.

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

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

The description is a single dense paragraph front-loaded with the core action and scope, followed by usage routing and parameter support. Every clause adds value; no filler or restatement.

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 filtered search tool with an output schema, the description is complete: it states the trigger condition, the alternative paths, the scope limitation, and the available controls (sort_type, duration_range, page_token pagination). Nothing needed to select and 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%, and each parameter has a detailed description, so the tool description only needs to mention that sort_type, duration_range, and page_token are supported. It adds no syntax beyond the schema, 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 opens with a clear verb and resource: '按搜索词搜索微信视频号视频' (search WeChat Channels videos by keyword). It also differentiates itself from siblings by noting it returns only videos, not image-text posts, and contrasts with detail/comment/speech-text 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?

Explicitly states when to use ('用户需要按搜索词查找视频时使用') and when not to: if a work link or valid encrypted_object_id is already available, use detail/comment or ID-based speech-text tools directly, '均无需先调用搜索'. This gives clear routing versus the many 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?

Annotations already indicate non-read-only, non-idempotent, and non-destructive behavior. The description adds valuable operational detail: it waits up to 240 seconds and, if incomplete, returns a job_id with a next-step query action. This goes beyond the structured annotations.

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

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

One dense sentence conveys the core action, parameter acquisition, and post-submit behavior without excessive verbosity. It is front-loaded with the main action and includes only necessary details, though the multiple clauses require attention.

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 submission tool, the description adequately covers how to obtain the parameter, the wait behavior, and the job_id fallback. An output schema is present, and annotations cover side effects, so no critical operational detail is missing. The 'next-step query action' is slightly vague but 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 coverage is 100% for the single parameter, and the description repeats the schema's explanation without adding new parameter semantics. The waiting and job_id behavior is not parameter-specific, so the 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 ('提交') and resource ('视频口播转文字任务') tied to encrypted_object_id, and it is clearly distinguished from the sibling wechat_submit_video_speech_text_by_video_url by the id-based parameter. It also explains where to obtain the id if not provided, reinforcing the purpose.

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 clear when-to-use guidance: use directly when the user provides the id, otherwise obtain it from wechat_search_videos or author works list. It does not explicitly mention the by_video_url sibling as an alternative, but the context is inferable from the parameter and 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?

Annotations already indicate this is a write operation (readOnlyHint=false) and non-idempotent. The description adds valuable behavioral context: it waits up to 240 seconds, returns a job_id if not completed, and instructs the next query action. This goes beyond what annotations provide and helps the agent understand the async nature of the task.

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 well-structured sentence that front-loads the action, then provides the timeout and job_id fallback. No filler words; every part is informative.

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 (return values are covered), and the description explains the async submission pattern, timeout, and job_id fallback. It does not explicitly name the next query tool (wechat_get_video_speech_text_job), but the sibling list makes it inferable. This is fairly complete for a submission tool.

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

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

The input schema fully describes the video_url parameter with examples and format details (100% coverage). The description adds no additional parameter semantics, and per the rubric, the baseline of 3 applies when schema coverage is high and the description doesn't 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 specific verb ('提交' – submit) and resource ('微信视频号视频口播转文字任务' – WeChat video channel speech-to-text task), making the purpose clear. However, it does not explicitly differentiate from the sibling tool 'wechat_submit_video_speech_text_by_encrypted_object_id' – the name itself hints at the by-URL distinction, but the description doesn't state it clearly.

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

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

There is no explicit guidance on when to use this tool versus the alternative submission tool by encrypted_object_id, nor any mention of prerequisites. The description only covers the post-submission behavior (wait, job_id), not the selection criteria. Agents must infer usage from the tool name alone.

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