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?

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds genuine scope context — that it returns only first-level comments and that results are paginated via an opaque token — but says nothing about rate limits, pagination termination, or auth requirements.

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

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

A single front-loaded sentence that leads with the action and resource, then appends the two optional capabilities. No redundancy or filler.

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

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

With an output schema present and annotations covering the safety profile, the description supplies enough to invoke the tool correctly. The minor omission is the lack of an explicit pointer to the sub-comments or URL-based alternatives, which the agent otherwise has to guess.

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

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

Schema description coverage is 100% and the schema already details note_id format rules, the sort_type enum values, and the page_token contract. The description merely restates that sort_type sorts and page_token pages, adding no semantics beyond the structured fields, 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 — retrieve first-level comments of a single note keyed by note_id — and the '一级评论' scoping cleanly separates it from the sibling xhs_get_note_sub_comments_by_comment_id. It is clear, though it never names or contrasts the URL-based twin (xhs_get_note_comments_by_note_url), so explicit sibling differentiation is left implicit.

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 statement of when to prefer this tool over the by_note_url variant, over sub-comments, or any prerequisite/exclusion. The description only lists what features exist (sorting, paging), leaving the agent to infer routing from the name alone.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that only first-level comments are returned and that sort_type/page_token are supported, but it does not characterize pagination limits or rate behavior beyond what the schema 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 single tight sentence with the resource and supported controls front-loaded and no filler. It is not padded, though it is also not richly structured beyond that one clause.

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, and the description covers input forms and controls. What is missing is any explicit routing against the note_id sibling, which is the only real completeness gap for this tool family.

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 sort_type's enum meanings and page_token's opaque-token rules are fully documented in the schema. The description only echoes that these parameters exist, adding no syntax or semantics beyond structured data.

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 (获取) and resource (单篇小红书笔记的一级评论), and the qualifier 一级评论 cleanly separates it from the sibling xhs_get_note_sub_comments_by_comment_id. The accepted input forms (链接/短链接/分享文案) also distinguish it from the by_note_id variant.

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

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

Usage is implied by the input types and the mention of 翻页, but there is no explicit when-to-use guidance versus the note_id sibling. An agent must infer the URL-vs-ID split from the name and schema rather than being told.

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 crucial behavioral rule beyond the readOnly/openWorld annotations: when note_url is non-null it must be preserved verbatim including query parameters, and when null no public URL should be synthesized from note_id. This is actionable, specific, and not inferable from the schema.

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

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

Two sentences with no filler: the first states the operation, the second states the critical URL-handling constraint. Important information is front-loaded and 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?

For a simple one-parameter read tool with an output schema, the description plus schema covers most needs. However, it is incomplete as a selection aid because it does not differentiate the tool from the sibling xhs_pgy_get_note_detail_by_note_id, and it lacks any mention of when a URL-based alternative would be preferred.

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 note_id parameter is already described in detail in the schema. The tool description only repeats that it uses note_id and adds no parameter-level meaning beyond the schema, 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 opens with a specific verb and resource: '根据 note_id 获取单篇小红书笔记详情' (get single Xiaohongshu note detail by note_id), which clearly identifies what the tool does and the identifier it keys on. This naturally distinguishes it from the sibling note_url-based 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?

No guidance is given about when to choose this tool over alternatives. It does not mention xhs_get_note_detail_by_note_url for URL inputs, nor does it explain the difference from xhs_pgy_get_note_detail_by_note_id, so an agent receives no routing help beyond the tool name.

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

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

Beyond the readOnlyHint/openWorldHint annotations, the description adds an important behavioral constraint: the returned note_url must be preserved exactly, including xsec_token, and must not be reconstructed from note_id. It also warns against synthesizing a public link when note_url is null, which is valuable execution-relevant information.

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

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

Two sentences: the first states the purpose and accepted inputs, the second front-loads the critical URL-preservation constraint. No filler or repetition.

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 single required parameter, full schema coverage, readOnly/openWorld annotations, and an output schema present, the description supplies the remaining necessary operational rule (preserve note_url as-is). No critical selection or invocation information 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?

The schema already provides 100% coverage of note_url's accepted forms. The description mostly restates those forms and adds a downstream URL-preservation rule rather than new input semantics, so it does not exceed the schema-documented baseline.

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

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

The description uses a specific verb ('获取') and resource ('单篇小红书笔记详情') with the input carrier (note_url) defined as link/short link/share text. This clearly distinguishes the URL-based detail retrieval from the sibling xhs_get_note_detail_by_note_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 clearly states the intended input forms (long link, short links, share text), so an agent knows what to pass. It does not explicitly name the note_id-based alternative or state when not to use it, but the context is clear enough that only URL/ID routing remains implicit.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that the tool supports page_token pagination, which is useful behavioral context, but it discloses nothing further about rate limits, auth, or result ordering—appropriate given the rich annotations and 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 front-loaded sentence opens with the purpose, then chains usage rules via semicolons. Every clause earns its place, though the run-on density slightly hurts scannability versus separate sentences.

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 covering return values, complete parameter documentation, and read-only annotations, the description only needs to convey the retrieval workflow and pagination—both present. It is essentially complete for this tool; only minor extras like expected reply ordering or depth limits are absent.

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 three parameters are documented extremely thoroughly in the schema itself (ID provenance, copy sources, page_token opacity rules). The description adds the recovery workflow for missing IDs but no parameter meaning 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?

The description states a specific verb (获取), a precise resource (二级评论/二级评论列表), and the exact keying scope (note_id + 一级评论 comment_id). It also implicitly distinguishes itself from the sibling xhs_get_note_comments_by_note_id/url tools by naming 二级评论 and referring to the 一级评论工具 as a separate step.

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

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

It gives explicit when-to-use routing: use directly when a complete valid ID pair is supplied, call the first-level comment tool to fill in a missing comment_id when only a note_id/note link exists, and ask the user when no note locator is available. This is a full decision tree, not mere implied usage.

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. The description adds useful input-scoping constraints (no links, spu_id, or search terms) and clarifies the ID source, but does not disclose response behavior or error conditions. This is adequate but not exceptional given the annotation coverage.

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

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

Two concise sentences front-load the core operation, then cover sourcing the ID and the alternative tool. No redundant wording; every sentence earns its place.

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

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

For a simple read-only tool with one parameter, full schema coverage, annotations for safety, and an output schema, the description covers the necessary source guidance and exclusions. Nothing essential 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?

The input schema covers the single parameter 100% with detailed semantics, including exact copying from search results and unsupported input types. The description largely repeats this guidance, so it adds little beyond the schema. Baseline 3 is appropriate.

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

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

The description clearly states the tool retrieves product details by sku_id, a specific verb + resource. It also explicitly differentiates itself from xhs_get_product_detail_by_url and lists unsupported identifiers (product links, spu_id, search terms), making its 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 explicitly states when to use the tool: directly when sku_id is available, or obtain the ID from xhs_search_products otherwise. It also names the alternative tool for link-based lookups and states exclusions, providing 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?

注解已声明 readOnlyHint=true 和 openWorldHint=true，因此安全行为已有覆盖。描述额外补充了行为上下文：接受短链接和分享文案、无需先搜索、返回的 sku_id 可复用，为调用决策提供了有价值的信息。

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

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

两句话毫无冗余，第一句直述核心功能和输入形式，第二句给出替代方案和后续用途。信息密度高且无浪费。

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?

工具只有一个参数、有输出 schema 和注解，描述已覆盖输入变体、与 SKU 工具的区分以及返回值复用路径。没有明显缺口，代理在需要调用时不会缺少关键信息。

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 对参数 url 的描述已非常完整，覆盖支持和不支持的链接类型（覆盖率 100%）。描述本身没有在 schema 之外增加新的参数格式细节，按基线给予 3 分。

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

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

描述明确说明工具功能：根据商品链接、短链接或分享文案获取商品详情，动词和资源清晰。还通过指向 xhs_get_product_detail_by_sku_id 的使用场景将自己与同类工具区分开来，避免歧义。

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

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

描述明确给出使用时机：已有完整 sku_id 时改用 xhs_get_product_detail_by_sku_id，无需先搜索，且指出返回的 sku_id 可继续用于商品评价工具。排除了替代方案并给出下游用途，属于显式指引。

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 readOnlyHint annotation already signals a non-mutating read, and the description adds valuable behavioral constraints: the next_page_token must be passed back verbatim, must not be truncated or modified, and root_review_id must not be supplied. These details go beyond what the annotations alone would provide.

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

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

The description is compact, front-loaded with the core operation, and every sentence adds needed guidance. The token integrity warning is specific and directly actionable rather than 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 two-parameter read-only tool with a supplied output schema, the description covers ID sourcing, parent-tool routing, first-page vs. continuation behavior, and an explicit exclusion of root_review_id. Nothing necessary for correct invocation 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 already documents review_id sourcing and exact page_token reuse rules. The main description mostly reinforces those rules rather than introducing new parameter-level meaning, so the baseline score 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 precise verb-and-resource pair: fetch replies under a top-level product review by review_id. It clearly distinguishes this tool from xhs_get_product_reviews and note-comment siblings by scoping to product review replies and rejecting root_review_id.

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

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

The description explicitly says to use an existing review_id directly and otherwise obtain one from xhs_get_product_reviews. It also explains pagination semantics and the continuation requirement, so an agent knows exactly when and how to invoke the tool.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, covering safety. The description adds valuable behavioral context: pagination semantics (token must be passed back unchanged, no truncation), the requirement to use the exact next_page_token, and the exclusion of root_review_id. It doesn't cover error handling or invalid tokens, but given annotation coverage, this is sufficient.

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

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

The description is a single, dense sentence that front-loads the purpose and then covers usage, token handling, and exclusions. It is efficient with no filler, though slightly run-on. The key information is packed clearly.

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 complexity (pagination with token integrity) and the presence of an output schema, the description covers all necessary usage aspects: purpose, ID sourcing, pagination protocol, and parameter exclusions. Nothing essential for correct invocation 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 coverage is 100% with both parameters documented. The description adds meaning beyond schema: it specifies the source for review_id (from xhs_get_product_review_replies) and the token integrity requirement (must be passed back unchanged). This enriches the parameter semantics beyond the schema descriptions.

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

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

States a specific verb (获取/get), resource (商品评价回复的嵌套回复/nested replies of a product review reply), and key parameter (review_id). Clearly distinguishes from sibling xhs_get_product_review_replies by specifying it retrieves replies to a reply, not top-level replies. Also explicitly excludes root_review_id, reinforcing scope.

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: if review_id is available, use directly; otherwise obtain it from xhs_get_product_review_replies. Names the exact sibling tool as the source for the required ID. Also provides pagination instructions (pass next_page_token back as page_token) and a negative constraint (does not accept root_review_id). These guidelines leave no ambiguity about when and how to invoke.

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 important behavioral detail beyond the readOnlyHint annotation, especially around pagination: the returned next_page_token must be passed verbatim as the next page_token, and pages cannot be truncated, abbreviated, masked, or replaced with ellipses. This is a concrete, actionable constraint that affects correct invocation.

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

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

The description is appropriately brief and well-ordered: it states the core operation first, then explains how to obtain the ID, then the support parameters and pagination behavior, and finally which inputs are not supported. Every sentence adds useful operational information.

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

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

Given that an output schema exists and the annotations already signal read-only and open-world behavior, the description covers all essential invocation details: how to get the required id, how to paginate correctly, and what not to pass. No critical usage gap remains.

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

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

Schema description coverage is 100%, so the input schema already documents all parameters. The description largely reinforces the same information, such as sku_id provenance and page_token integrity, without adding significant new meaning beyond what the schema provides.

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

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

The description explicitly states the tool's function — 根据小红书商品 sku_id 获取商品评价 — giving a specific verb, resource, and identifier type. It also differentiates from other tools by stating what it does not support: 商品链接、spu_id 和搜索词, and it points to xhs_search_products as the source for missing sku_id values.

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

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

The description provides a clear usage rule: 已有该 ID 时直接使用，否则可从 xhs_search_products 获取. This tells the agent when to use this tool directly and when to first call another tool. It also gives a strong when-not cursor by rejecting product links, spu_id, and search terms as inputs.

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. The description does not contradict these, but it adds no additional behavioral context—e.g., whether the list updates frequently, whether it requires authentication, or what happens if the list is unavailable. With annotations covering the key traits (read-only, open world), the lack of further detail is acceptable but not enhanced.

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 in Chinese. It conveys the purpose efficiently without any filler. However, it could be slightly less terse if it included the English equivalent for non-Chinese agents.

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

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

Given the tool has no parameters and has an output schema, the description is sufficient for understanding the tool's purpose. The output schema presumably defines the structure of the hot list, so the description does not need to explain return values. One might wish for additional context about what 'hot list' means (e.g., trending topics, searches), but the purpose is clear enough.

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

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

The input schema has zero parameters, so the description cannot add parameter details. With no parameters, the baseline is 4—the description is sufficient as there are no parameter semantics to elaborate.

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

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

The description clearly states the tool gets the 小红书 search hot list (search hot list for Xiaohongshu). The verb '获取' (get) and resource '搜索热榜' (search hot list) are specific. Among sibling tools that focus on notes, comments, user info, products, and search results, this one uniquely addresses the hot list, providing good differentiation.

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 this should be used when an agent or user wants the current trending/search hot list from Xiaohongshu. However, it does not explicitly state when to use this versus alternatives (e.g., when to prefer this over search functions like xhs_search_notes). No exclusions or context about frequency or user need are given.

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

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

Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds that the call supports sorting and pagination, which is mild behavioral context, but it does not go beyond that with e.g. what happens on invalid page_id, data volume, or the meaning of open-world results.

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: core action and identifier first, then the two capability notes. Every word earns its place, and there is zero redundant restatement of the tool name or schema fields.

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

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

For a read-only list tool with 3 parameters (1 required), a full output schema covering return values, and annotations covering safety, the description is adequate. The one meaningful gap is not referencing xhs_get_topic_notes_by_topic_url so the agent can route by identifier type (page_id vs topic_url), though the sibling names largely communicate this.

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 page_token schema description is exceptionally detailed (opaque token, no reuse across page_id/sort, no modification). The tool description merely mentions sort_type and page_token by role, adding no meaning beyond what the schema already provides, so the high-coverage 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 + resource: '获取标签页笔记列表' (get tag page notes list) keyed by page_id, plus the two capabilities sort and pagination. It is clear but does not explicitly differentiate from the very close sibling xhs_get_topic_notes_by_topic_url; the distinction is left to the tool name rather than stated in the description.

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

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

The phrase '根据 page_id' implies the tool is for cases where the agent holds a page_id, and the pagination rules are well documented in the page_token schema description. However, the description never explicitly says when not to use it nor names the URL-based alternative, so routing guidance is implied rather than stated.

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

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

Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds only that sorting and pagination are supported, which is already visible in the schema; it contributes little extra behavioral context beyond 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?

A single sentence states the purpose and key capabilities with no filler. Every element in the description 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, output schema, and read-only annotations, the description is sufficient for an agent to select and invoke the tool correctly. It could add an explicit pointer to xhs_get_topic_notes_by_page_id for page-ID scenarios, but that is a routing nicety, not an invocation gap.

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

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

Schema description coverage is 100%, so the schema already documents topic_url formats, sort_type enum, and page_token behavior. The description only restates that sorting and pagination are supported, adding no new meaning beyond the schema.

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

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

The description states a specific verb and resource: it fetches the topic notes list from a topic URL, short link, or share text. This also differentiates it from the sibling xhs_get_topic_notes_by_page_id, which uses a page ID instead of a 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?

The description makes the intended trigger explicit: use this tool when the caller has a topic page link, short link, or share text. It does not mention the page_id alternative or state exclusions, so it misses the full 'when not to use' 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?

The annotations already declare readOnlyHint=true and openWorldHint=true, indicating a safe read operation. The description, though brief, adds valuable context by specifying the required format of the encrypted user ID (29-bit lowercase hex). However, it doesn't disclose potential failure cases or error behavior, but given the annotations, the bar is lowered and this additional format detail justifies a 4.

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 unnecessary words. It is front-loaded with the main action and outcome, and the parameter schema handles all additional details, making it optimally concise.

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

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

Given the tool has one parameter with a rich schema description and an output schema (as indicated by context signals), the description is sufficient for understanding the input and expected result. It doesn't describe return values, but since an output schema exists, that is not required. The main missing piece is explicit mention of use-cases or limitations, but it's still complete enough for an agent to call 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 schema description coverage is 100%, so the schema already documents the parameter thoroughly. The description does not add further semantics beyond what the schema provides, so a baseline score of 3 is appropriate.

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

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

The description clearly states the verb '获取' (get) and the resource 'user_id' derived from an encrypted user ID, which is distinct from other tools that fetch user info by profile URL or user ID. It precisely identifies the input and output, making it easy for an agent to understand its 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?

While the description doesn't explicitly mention when to use this tool over alternatives, the parameter schema provides strong guidance by explicitly stating what not to pass (24-bit user_id, nickname, etc.). This is clear context but lacks an explicit alternative tool reference, so it doesn't fully reach a 5.

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

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

Annotations already declare readOnlyHint=true (safe read) and openWorldHint=true (results may vary). The description adds valuable behavioral context beyond annotations: it clarifies that the tool accepts multiple URL formats and share text, and explicitly prohibits note links. No contradictions 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 a single sentence that directly states the tool's purpose and input options. It is concise and front-loaded, with no wasted words. Could slightly improve by adding a brief usage hint, but overall efficient.

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

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

Given the tool's low complexity (one parameter, output schema present, annotations provided), the description is fully adequate. It specifies the allowed input formats and what to avoid, while the output schema covers return values. No gaps remain for an agent to use this tool 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 input schema covers 100% of parameters, with a detailed description of the 'profile_url' parameter. The tool description repeats the supported formats but adds no new semantic meaning beyond what the schema already provides. Baseline 3 is appropriate.

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

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

The description clearly identifies the action ('get') and resource ('single Xiaohongshu user info'), and specifies the input type (profile link, short link, or share text). This distinguishes it from sibling tools like 'xhs_get_user_info_by_user_id' (which takes a user ID) and 'xhs_get_user_posted_notes_by_profile_url' (which retrieves notes, not user info).

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

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

The description implicitly suggests usage when a profile URL is available, and the schema explicitly warns not to pass note links. However, it does not explicitly compare to alternatives or state when to use this tool versus 'xhs_get_user_info_by_user_id' or other siblings. The guidance is present but not 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=true and openWorldHint=true, so the agent knows this is a safe read operation in an open world. The description itself adds no further behavioral context (e.g., error handling, rate limits), but this is acceptable given the annotations cover the safety profile. No contradiction 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?

The description is a single, concise sentence that immediately conveys the tool's purpose. There is no extraneous information, and all additional guidance is appropriately placed in the schema, keeping the description lean and front-loaded.

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

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

The tool has a single parameter fully documented in the schema, annotations declare safety traits, and an output schema exists so return values are separately specified. The description is complete for a simple, read-only lookup tool—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%, and the user_id parameter is thoroughly documented with a description explaining origin, alternatives, and exclusions. The tool description adds no additional parameter semantics, but the schema already carries the full burden, so baseline 3 is appropriate.

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

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

The description '根据 user_id 获取单个小红书用户信息' clearly states the action (get) and resource (single Xiaohongshu user info) and specifies the input method (by user_id). It distinguishes itself from the sibling tool xhs_get_user_info_by_profile_url via the parameter schema's note about using profile_url for home page links, so an agent can tell them apart.

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 parameter description explicitly provides usage guidance: it instructs to use user_id as-is when provided, where to copy it from other results, and specifically says '如果只有主页链接，请使用 profile_url 入口' (if only home page link, use profile_url), while also warning against using Xiaohongshu number, nickname, or homepage name. This clearly routes the agent to the correct tool and input.

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 readOnlyHint and openWorldHint, so the safety profile is established. The description adds that the operation supports page_token pagination, which is a behavioral trait beyond the annotations. However, it does not disclose ordering, visibility of returned notes, rate limits, or response behavior beyond pagination, and the deeper token constraints live in the schema rather than the description.

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

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

The description is a single compact sentence that front-loads the verb, resource, and accepted input forms, then states pagination support. It is concise, scannable, and contains no redundant 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 detailed input schema, an output schema, and readOnly/openWorld annotations, the tool definition is largely sufficient for correct invocation. The only notable gap is the absence of explicit guidance for choosing between this tool and closely related siblings, though the tool name and parameter type make the decision mostly unambiguous.

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%: profile_url documents long links, short links, and share text, and page_token fully documents the opaque, same-user-only, must-be-returned-unmodified rules. The description only restates the accepted link forms and pagination support, adding no new parameter meaning beyond the schema.

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

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

The description clearly states the action (获取, 'get'), the resource (用户已发布笔记列表, 'list of user's published notes'), and the accepted input forms (主页链接/短链接/分享文案). It also mentions page_token pagination. The input-type distinction differentiates it from sibling xhs_get_user_posted_notes_by_user_id even without naming it.

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

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

The description implies use when the agent has a profile URL, short link, or share text and needs a user's published notes. The profile_url parameter additionally instructs '不要传笔记链接' (do not pass note links), which is a useful exclusion. However, there is no explicit mention of when to prefer this tool over siblings like xhs_get_user_posted_notes_by_user_id or xhs_get_user_info_by_profile_url, leaving alternative selection 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?

注解已声明 readOnlyHint=true 和 openWorldHint=true，说明这是只读操作且结果可能超出已知集合。描述额外补充了翻页行为：首次留空、后续必须传回完整 next_page_token，且令牌不能跨用户复用、不得修改。这些对 agent 正确调用很重要。但描述未提及返回结构或可能的错误情况，考虑到注解已覆盖安全性，评分为 3 合理。

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

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

描述一句话点明核心功能，简短高效。关键的使用规则（翻页）放在描述中，而详细参数语义放在 schema 中，整体结构合理。唯一不足是描述没有提及与 profile_url 版本的区别，但参数说明中已补充，不影响简洁性评分。

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?

工具复杂度中等，有输出 schema 且注解完整，描述已覆盖核心调用方式（user_id + 翻页）。缺少的可能是对返回字段的简要说明，但输出 schema 已承担该职责。考虑到 openWorldHint=true，描述不需要列举所有可能结果，整体对 agent 正确调用已足够。

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

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

schema description coverage 为 100%，两个参数在 schema 中已有详细说明，尤其是 user_id 的来源优先级和 page_token 的完整使用规则。描述本身没有在 schema 之外增加新的参数语义，因此按高覆盖基线评 3 分。

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

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

描述明确说明通过 user_id 获取用户已发布笔记列表并支持 page_token 翻页，动词和资源清晰。与兄弟工具 xhs_get_user_posted_notes_by_profile_url 形成明确区分，一个按 user_id、一个按 profile_url，agent 无需打开 schema 即可区分。

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

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

描述虽未直接写'当有其他入口时用哪个'，但结合 user_id 参数说明中的详细指引（用户已提供则原样使用；否则可从其他结果复制；只有主页链接时用 profile_url 入口），隐式给出了与 xhs_get_user_posted_notes_by_profile_url 的选择依据。缺少明确的'何时不用'声明，但上下文已足够指导选择。

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 the readOnlyHint and openWorldHint annotations, the description discloses the blocking wait behavior ('每次最多等待 240 秒' - wait up to 240 seconds each time) and the idempotency traits (no re-processing, no re-submission). These are valuable behavioral details not captured by annotations. It does not describe what happens on timeout, but the output schema covers return structure.

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

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

The description is a single, well-structured sentence that front-loads the primary action and then adds usage, timeout, and exclusion guidance. It is dense but not verbose, with every clause earning its place. A 4 reflects that it is efficient while slightly dense; could be split for readability but is far from under-specified.

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 there is an output schema, the description adequately covers the essential operational context: when to use, the blocking wait, and explicit prohibitions against resubmission and re-processing. It implies repeated calls are allowed ('每次最多等待' - each time). No critical information for correct invocation is missing, making it complete enough.

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

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

The input schema has 100% coverage and already thoroughly explains the job_id parameter, including instructions on sourcing it from the user or submission tool and not passing note_id. The description essentially repeats this without adding new semantics. Baseline 3 is correct since the schema does the heavy lifting.

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

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

The description clearly states the action: '查询任务状态' (query task status) for a specific resource, the job_id. It explicitly mentions it is used to continue unfinished tasks, which distinguishes it from the sibling submission tools (e.g., xhs_submit_video_speech_text_by_note_id). The purpose is unambiguous and specific.

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 when-to-use context: '用于继续未完成任务' (used to continue unfinished tasks). It also gives exclusions: '不要重复提交任务' (do not resubmit tasks) and '不触发重处理' (do not trigger re-processing), implicitly steering the agent away from the submission siblings. However, it does not explicitly name the alternative submission tools, so a 4 is appropriate rather than 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 only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: success deducts 20 points, failure is free, results are returned directly with business fields and points, no date filter is supported and the cutoff date is not provided, store visits do not equal orders/deals, and cost estimates do not represent actual transaction cost or ROI. These are exactly the cautions an agent needs before invoking.

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?

Purpose is appropriately front-loaded, but the definition is long and the daily/cooperation explanations, caveats and cost notes repeat material already present in the schema parameter descriptions. Several sentences could be trimmed without losing routing information, so it is functional rather than tight.

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, and the description still adds the point-cost model and the key semantic caveats. Combined with full schema coverage and clear sibling routing, an agent has what it needs; only the redundancy noted above keeps it from being exhaustive.

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

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

Schema description coverage is 100%, so the baseline is 3. The description reinforces the scope semantics (daily is not per-day aggregation; outputs echo the actual scope; note_count cannot be read as the selected scope's note count) but this text largely duplicates the note_scope schema description verbatim, so it adds little the schema does not already carry.

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 (蒲公英创作者商业概览) and enumerates exactly what the overview contains: note scale and median, service performance, platform tags, growth, estimated cost and comparison values. It also explicitly names the sibling tools it is not (逐篇表现/创作者笔记表现工具, 资料与报价/创作者档案工具, 粉丝构成/粉丝画像工具), so an agent can route 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 explicit when-to-use (查询指定日常/合作口径的商业汇总与成本参考), explicit when-not (不返回逐篇明细, 不支持指定日期), and names the alternative tools for each excluded need. The daily vs cooperation selection rule is stated as a decision: daily for everyday content performance, cooperation for brand/商单/sponsored notes or store-overflow summaries.

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 only declare readOnlyHint and openWorldHint; the description adds substantial context beyond them: platform-default statistics range with no date override, distribution not guaranteed complete and not usable to derive follower counts, returns profile fields plus points, 20-credit deduction on success and no charge on failure. These cost and limitation disclosures are exactly the behavioral detail annotations cannot convey.

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

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

Four tightly packed lines, front-loaded with purpose then routing, limitations, and billing. Every sentence carries distinct information 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?

With annotations covering read-only/open-world behavior and an output schema present, the description supplies the remaining essentials: intended scope, sibling routing, statistical caveats, and credit cost. Nothing needed to invoke or interpret the call 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 coverage is 100% and the single user_id parameter is fully documented in the schema (pattern, sourcing rules, prohibited inputs). The description adds only the '完整 user_id' emphasis, which largely restates the schema constraint, so baseline 3 is appropriate.

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

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

States a specific verb and resource (获取小红书蒲公英创作者粉丝画像) and enumerates the exact dimensions returned (年龄、性别、地域、城市、兴趣、设备品牌及数据日期). It explicitly distinguishes itself from the fans-summary and creator-profile siblings, so an agent can route correctly without opening 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?

Explicitly states when to use it (查询粉丝构成时使用) and names the alternatives with their conditions: 粉丝规模、增长、活跃、阅读和互动 use the fans summary tool, and 创作者资料和报价 use the profile tool. Covers both when-to-use and when-not-to-use.

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 the readOnlyHint/openWorldHint annotations, the description discloses cost behavior (成功调用扣减 20 积分，失败不扣费), the success return shape (汇总字段和 points), and a substantive data limitation (增长周期及统计窗口截止日期未提供，不能按查询日期推算). This is exactly the extra operational context annotations cannot carry.

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?

Front-loaded with purpose, then usage/alternative, then data limitations and billing. Every sentence carries signal, though the date/window disclaimer is lengthy and slightly repetitive (不支持指定日期 and 不能按查询日期推算 overlap).

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 detailed, and the readOnly/openWorld annotations cover the safety profile. With cost, alternative routing, and data-scope caveats all present, an agent has everything needed to call 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 coverage is 100% for the single user_id parameter and it is fully documented in the schema (including format and anti-patterns). The description only reinforces that a complete user_id is required, adding minimal meaning 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?

States a specific verb (获取) and a well-enumerated resource set (粉丝总数、平台增长指标、活跃/阅读/互动粉丝人数及占比), and explicitly names the sibling it is not (粉丝画像工具). An agent can distinguish this from xhs_pgy_get_creator_fans_profile without reading 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 trigger (查询粉丝规模和活跃情况时使用) and routes the other case to a named alternative (年龄、性别、地域和兴趣等构成使用创作者粉丝画像工具). It also states exclusions (不支持指定日期或统计周期), 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?

Beyond the readOnlyHint/openWorldHint annotations, it discloses cost behavior (成功扣减 20 积分，失败不扣费), data semantics (median values, cooperation scope includes 进店 fields while daily returns null, no cross-date summation, missing dates are not zero-filled), and response shape (business fields plus points). These are material operational facts an agent cannot infer from 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?

Dense but front-loaded: purpose, then usage, then behavioral caveats. Every clause carries information, though a few points (口径不可混用, 成本口径见字段说明) are repeated across description and schema, adding mild 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 not be enumerated, and the description still confirms what success returns. Combined with cost semantics, scope caveats, and explicit sibling routing, an agent has everything required to call 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 baseline is 3; the description adds meaning by explaining what the cooperation vs daily scopes imply for 进店 fields and consumption rules. It reinforces the '不可混用' constraint but largely echoes the schema's own note_scope description, so it stops short of a 5.

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

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

States a precise verb and resource: fetching date trends and overviews of XHS Pgy creator exposure, reads, interaction medians and estimated cost. It scopes what is fixed (图文＋视频, 近30日, 全流量) and explicitly names the sibling tools that cover adjacent needs (商业概览 and 笔记表现), so an agent can distinguish it without opening 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?

Explicitly gives the trigger condition ('观察指标随时间变化时使用'), the selection rule for note_scope (daily vs cooperation), the hard exclusion ('不支持自选日期'), and routes split-by-format/commercial totals to 商业概览工具 and per-note performance to 笔记表现工具. When-to-use, when-not, and alternatives are all present.

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 only cover readOnly and openWorld, so the description carries the behavioral load and does so richly: 20-credit cost on success / no charge on failure, fixed 30-day window with no custom date or note-type selection, detail capped at 15 notes (not exhaustive), and an explicit semantic caveat that 0 values for video-completion/3s-read fields are not real zeros. It also warns that notes[] *_benchmark_rate can be negative or >1 and must not be mixed with the summary-level 0-1 fields.

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?

Front-loads the purpose and the fields returned, then layers usage, caveats, and cost. Some phrases (固定近30日、图文＋视频、全流量) are restated from the schema description, but overall every sentence carries operational meaning and is well signposted.

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 prose, and the description still supplies everything an agent needs to call correctly: required-id sourcing rules, cost, fixed analytical window, detail cap, and field-semantics traps. Nothing material is left to guess.

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 user_id (format guidance) and note_scope (enum semantics, default, fixed scope) are already fully documented in the schema. The description adds scope constraints around the call but nothing per-parameter beyond what the schema states, 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) and resource (蒲公英创作者笔记表现) and enumerates the returned metric families (曝光/阅读/互动中位数、互动率、完播率、图文3秒阅读率、内容标签、笔记明细). It explicitly distinguishes itself from siblings by naming the commercial-overview and creator-profile tools. An agent can identify scope 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?

Gives explicit when-to-use ('查询日常或合作笔记表现及最近明细时使用') and routes two adjacent needs to named alternatives (商业汇总→商业概览工具, 资料和报价→创作者档案工具). No inference required to pick this over its siblings.

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

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

Annotations only cover readOnlyHint/openWorldHint; the description adds non-obvious behavior — a 20-credit charge on success with no charge on failure, RMB-denominated quote units, and the caveat that a zero value does not mean free collaboration. These are exactly the operational facts annotations cannot express.

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?

Field list, routing rules, and caveats are front-loaded and each sentence carries information; it is dense but no sentence is filler. Slightly long for a single-parameter tool, keeping it from a 5.

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

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

An output schema exists so return fields need no elaboration, and the description still confirms success returns profile fields and points. With cost, units, and sibling routing all covered, an agent has everything needed to call 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?

Schema description coverage is 100% and the pattern/format guidance is already in the schema, so the baseline is 3. The description reinforces that a complete user_id is required but adds no syntax beyond what the schema states.

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

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

States a specific verb and resource (获取蒲公英创作者档案/报价) and enumerates the exact payload: 粉丝与商业笔记规模、合作行业、阅读与互动中位数、内容分类、特征标签、图文/视频报价. An agent can distinguish this from xhs_get_user_info_by_user_id purely from the text.

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 routes the agent: use this for PGY creator profiles and quotes, use user-info tools for ordinary accounts, and names four siblings (笔记表现、粉丝画像、指标趋势) with the condition that selects each. Nothing 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 mark readOnlyHint=true, and the description adds substantial behavioral context: successful calls deduct 20 积分, failed calls do not, the data is commercial and differs from public note details, zero quotation values do not mean free collaboration, and timeout/auth/insufficient-balance errors do not imply the creator is not入驻蒲公英. 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 front-loaded with the core purpose and payload, then moves to usage boundaries, cost, and error handling. Every sentence carries operational value; there is no filler, even though the text is longer than average.

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

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

For a tool with one parameter, an output schema, and annotations, the description covers all agent-relevant context: when to use, what it returns, cost, failure semantics, unavailable-data handling, and how it differs from ordinary note details. Nothing critical 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 coverage is 100%: the single note_id parameter already has a rich description covering how to obtain it and forbidding truncation/formatting. The description only repeats “根据 note_id,” so it adds little beyond the schema, which matches the baseline for high schema coverage.

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

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

The description opens with a specific verb and resource: “根据 note_id 获取小红书蒲公英单篇笔记商业增强详情” and enumerates the exact fields returned (正文、图片/视频摘要、作者、曝光量、阅读量、点赞、收藏、评论、分享、报价). It also explicitly contrasts itself with the ordinary detail tool, so an agent can distinguish it from sibling xhs_get_note_detail_by_note_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?

Usage is explicit: use only for 蒲公英入驻博主 notes, and use when the user explicitly requests 蒲公英 commercial data; ordinary note details should use the ordinary detail tool. It also gives a concrete clarification rule when the user mentions 曝光量/阅读量/报价 without an explicit 蒲公英 context, and warns against retrying when pgy_commercial_data_unavailable is returned.

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 the readOnlyHint/openWorldHint annotations, the description discloses the 20-point success cost, no charge on failure, that zero quotes do not mean free cooperation, and that timeout/auth/balance errors do not imply the creator is not onboarded. This is substantial behavioral context that annotations alone do not provide.

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 dense but every sentence serves a distinct purpose: scope, eligibility, disambiguation, cost, and failure semantics. The most important commercial and usage distinctions are front-loaded, and the structure supports quick agent 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?

Given this is a paid, commercial-scoped tool with special error semantics, the description is complete: it covers what data is returned, when to use it, how to handle ambiguous requests, cost implications, and error interpretation. The output schema handles return-value details, so nothing critical 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?

The input schema already covers note_url at 100%, including supported long links, short-link domains, and share copy. The description mostly restates '笔记链接、短链接或分享文案' without adding new parameter semantics beyond what the schema provides, so it stays at the baseline.

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

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

The description clearly states the tool retrieves Xiaohongshu Pingguo commercial enhanced note detail via note URL/short link/share text, and enumerates the returned metrics. It also differentiates itself from ordinary note detail tools and from the note_id variant, so an agent can select it unambiguously.

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 this tool: only for notes by creators already onboarded to Pingguo, and only when the user explicitly requests Pingguo commercial data; ordinary note details should use the normal detail tool. It also provides a disambiguation rule for vague metric requests and says not to retry with a different link entry when pgy_commercial_data_unavailable is returned.

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 only supply readOnlyHint and openWorldHint. The description adds substantial behavior beyond them: each item is an image tied to a note with possible multiple images per note (deduplication semantics), ranking is by platform relevance, exact keyword inclusion is not guaranteed, recall is not guaranteed, and pagination via page_token is best-effort. This is exactly the kind of honest behavioral disclosure the dimension rewards.

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?

Purpose is front-loaded and each clause carries weight (routing to siblings, pagination caveat, ranking/recall caveats). It is a dense run-on paragraph, however, and the multi-clause structure is slightly harder to scan than a bulleted or split form would be.

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 needed. Combined with the annotations, the description covers routing, pagination, ranking, and recall limits, leaving nothing an agent needs to call this tool 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 coverage is 100%, so both parameters are already documented, giving a baseline of 3. The description adds a genuine nuance beyond the schema on page_token ('可用于尝试下一页，不保证下一页有结果'), clarifying that pagination may yield no results. That extra meaning lifts it above 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+resource+scope (搜索小红书图片 / search Xiaohongshu images by keyword). It explicitly distinguishes itself from sibling tools: detail tools for when a note link/note_id already exists, and xhs_search_notes variants for image-text vs video notes. An agent can route correctly 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 explicit when-to-use (keyword image search), when-not-to-use (already have link/note_id → detail tools), and names the two concrete alternatives with parameters (xhs_search_notes(note_type="image") and note_type="video"). Nothing 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 cover readOnlyHint and openWorldHint, so safety is already declared; the description adds real behavioral context beyond them – the pagination round-trip contract (pass the full next_page_token back verbatim) and the hard requirement to preserve the full note_url including xsec_token. It stops short of describing rate limits, result caps, or failure modes, so it is strong but not exhaustive.

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?

Front-loaded with purpose, then routing, then parameter pitfalls, then the URL-preservation rule – a sensible order. It is somewhat long and repeats the 'do not truncate/mask the token' warning that already appears in the schema, which costs a little efficiency, but every remaining sentence carries a distinct instruction.

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 the description need not explain returns, and annotations cover the safety profile, so what remains – search scope, routing to alternatives, pagination and URL handling rules – is largely delivered. It is nearly complete, missing only sort_type guidance and any note on result volume or failure behavior.

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

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

Schema description coverage is already 100%, so the baseline would be 3; the description adds value on top by giving usage examples for note_type (image/video), warning about the publish_time_range naming trap, and stating that page_token must be reused verbatim for the same keyword/sort/type/time chain. The only untapped param is sort_type, which the description never mentions.

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

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

The description opens with a specific verb+resource (搜索小红书笔记) and immediately scopes what is included (普通、图文和视频笔记). It explicitly names the sibling it is not (xhs_search_images) and routes detail/comment/speech-text requests to the appropriate other tools, so the agent can distinguish it 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?

Explicit when-to-use and when-not-to-use rules are given: single-image search goes to xhs_search_images, existing link/note_id goes to the detail tools, comments/replies/speech-to-text go to the URL/ID tools. It also pre-empts common misuse by stating the filter parameter is publish_time_range (not publish_time) and that max_items is not accepted.

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 this as read-only and open-world, so no contradiction exists. Beyond that, the description adds important behavioral constraints around page_token handling: the full next_page_token must be passed back unchanged, with explicit prohibitions against truncation, abbreviation, masking, or replacing content with ellipsis. This is valuable behavioral context for the agent.

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 front-loaded with the core purpose and usage condition before moving to token-handling warnings. It is somewhat repetitive with the schema's page_token constraints, but it remains readable and each sentence earns its place in guiding tool selection and correct 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?

The tool is simple with only two parameters, one of which is optional, and an output schema is present. The description covers when to use it, when to prefer alternatives, and the critical pagination behavior, so an agent has everything needed to call 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?

Schema description coverage is 100%, and the schema already thoroughly documents both keyword and page_token, including the exact-copy requirement and what must not be passed. The description essentially repeats this rather than adding new parameter meaning, 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 opens with a specific verb and resource ('搜索小红书商品' – search Xiaohongshu products) and immediately states the primary use case: finding products by search term. It distinguishes itself from siblings by explicitly routing sku_id cases to product detail/review tools and link/share-text cases to xhs_get_product_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?

The description gives explicit when-to-use guidance: use when the user needs to find products by search word. It also names alternatives for complete sku_id and for product links/share text, and it explains pagination usage. This leaves little ambiguity about 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 the tool's safety and open-world nature are covered. The description adds that it returns 'candidate search suggestions', but does not elaborate on specific behaviors such as response format or limitations. This adds some but not rich context, aligning with baseline given 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, compact sentence that both defines the tool and differentiates it from alternatives. No wasted words, and the core information is front-loaded.

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

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

With a simple single-parameter tool, an output schema exists, and annotations cover read-only/open-world, the description is complete enough. It clearly states the purpose, usage, and exclusions. It does not address potential response times or error conditions, but these are not necessary for a tool of this simple nature and the presence of output schema reduces that need.

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

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

Schema coverage is 100% and the parameter description explicitly instructs what to pass (keyword or phrase being typed) and what not to pass (links, IDs, tokens). The description reinforces the schema, but also clarifies the intended input type (being typed) beyond the generic 'search term'. This adds practical guidance, slightly above baseline.

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

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

The description clearly states the tool retrieves candidate search suggestions based on the search term, with the explicit purpose 'to complete search terms'. It distinguishes itself from xhs_search_notes and xhs_search_products by naming them as alternatives for actual searches, making it clear what this tool does not do.

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 covers when to use the tool (for completing search terms) and when not to use it: when the user needs to actually search notes or products, directing to xhs_search_notes or xhs_search_products. This provides clear context and alternative tools, leaving no ambiguity.

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 operation read-only and open-world. The description adds useful behavior beyond annotations: pagination is supported, and continuing pages require keeping keyword unchanged and passing the previous next_page_token untouched. 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 two short clauses with no filler, opens with the core action, and front-loads the key routing guidance before pagination details.

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

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

For a simple read-only search tool with a complete output schema, full parameter documentation, and sibling context, the description covers the use case, exclusions, and pagination behavior. Nothing essential for invoking 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 the baseline is 3; the schema already explains keyword and page_token semantics. The tool description mostly restates that keyword searches users, accounts, or bloggers and does not add new parameter-level meaning.

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

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

The description states a specific action and resource: searching Xiaohongshu users, accounts, or bloggers by keyword, with pagination support. It also explicitly differentiates from user-profile tools when an ID or profile link is already available, helping an agent choose among siblings.

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

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

It states when to use the tool (keyword-based user search) and when not to (when a user_id or profile link is already known, use the user profile tool). The keyword parameter's 'do not pass profile link, user_id, or pagination token' further clarifies boundaries.

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 mutating, non-idempotent operation. The description adds valuable behavioral details: it waits up to 240 seconds, returns a job_id when incomplete, and tells the agent to perform a follow-up query. It does not contradict any annotations; the added info is complementary.

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 front-loads the action and then states the waiting behavior and the fallback return. No filler words; 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 one parameter, an output schema present, and sibling tools for follow-up, the description covers the essential workflow: submit, wait, and query next. It does not explicitly name the exact follow-up tool, but the mention of a 'next query action' is sufficient for an agent to infer the step, especially with sibling visibility.

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 note_id is highly detailed (100% coverage), specifying how to obtain it and what not to do with it. The tool description adds no additional parameter semantics beyond what the schema already provides, so the baseline of 3 is appropriate.

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

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

The description states a specific verb ('submit'), a clear resource ('video note speech-to-text task'), and the identifier type (note_id). It also distinguishes from the sibling tool that uses note_url, making the purpose unambiguous and separable from the other submission 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 implies use when you have a note_id, but does not explicitly mention the alternative (xhs_submit_video_speech_text_by_note_url) or when to choose one over the other. It provides no explicit usage exclusions, but the sibling tools are visible to the agent, so the context is partially inferred.

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 flag this as a write operation (readOnlyHint=false, idempotentHint=false). The description adds valuable behavioral detail beyond annotations: it explicitly mentions a 240-second wait and that an incomplete job returns a job_id and points to a next query action. This goes beyond the structured hints and clarifies the asynchronous 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?

The description is a single, dense sentence that front-loads the core action (submit task by note URL) and immediately covers the key constraints (wait time, job_id return). Every phrase earns its place; there is no filler or redundancy.

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

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

Given the available output schema (not shown but indicated), the description provides sufficient context: it states the input format, the asynchronous wait, and the follow-up query action. It does not explicitly name the polling tool (e.g., xhs_get_video_speech_text_job), but the existence of such a sibling and the mention of 'next query action' make the workflow clear. Minor gaps like error handling or idempotency advice are not critical given the annotations.

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

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

The schema description coverage is 100%, so the parameter note_url is fully documented. The tool description repeats the same input formats (link, short link, share text) without adding new syntax details. With schema doing the heavy lifting, a baseline 3 is appropriate.

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

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

The description clearly states the action (submit a video speech-to-text task), the resource (Xiaohongshu video note via URL, short link, or share text), and distinguishes it from the sibling by_note_id variant. It also outlines the wait/response behavior, leaving no ambiguity about the tool's 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?

The description provides clear context (it is a submission task triggered by a note URL), but it does not explicitly state when to prefer this over the by_note_id sibling or exclude other tools. However, the naming and input type make the usage context obvious enough for an agent to infer the appropriate choice.

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