Server Quality Checklist

Tool Scores

• temu_mall_searchA
  4.5/5.0
  Behavior5/5

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

  With no annotations, the description carries the full transparency burden and does so extensively: it discloses default-site behavior, ID trust constraints, sort-preset semantics, growth-rate decimal vs sellthrough percent scales, derived-metric denominator handling, incomplete-pagination labeling, and the requirement to bind linkUrl rather than construct URLs. These are meaningful behavioral constraints beyond simple search semantics.

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

  Conciseness4/5

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

  The description is a dense single paragraph, but every sentence contributes a distinct rule or context—site default, category ID trust, preset mapping, scaling conventions, evaluation caveats, sample marking, and linkUrl binding. It is front-loaded with the core purpose and then organized by operational concern, though a bulleted structure would improve scannability.

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

  Completeness4/5

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

  For a complex store-search tool with many sort/filter combinations, the description is unusually complete: it covers presets, site dependency, ID provenance, metric interpretation, pagination honesty, and output presentation. The presence of an output schema reduces the need to describe return fields. It loses one point for not explicitly contrasting with sibling search tools and not explaining authentication/rate-limit behavior, which are the only substantive gaps.

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

  Parameters4/5

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

  Although the nested schema has its own per-field descriptions, the context signal reports 0% schema description coverage at the top level, so the description must compensate. It adds semantic value by explaining the four presets in terms of sort fields, the '二选一' relationship between keyword and catIds, exact rate/percent formats, and '用户条件优先' priority. It does not enumerate every min/max pair, but the schema already covers those mechanically.

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

  Purpose5/5

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

  Description opens with '搜索 Temu 店铺名称或店铺 ID，筛选...'—a specific verb and resource (store search) with explicit filter dimensions and sort presets. It clearly differentiates itself from sibling tools like goods/image/review searches by focusing on mall/store-level metrics.

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

  Usage Guidelines4/5

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

  Provides strong operational guidance: default site 48, '未指定站点时使用美国站 48；其他国家先调用站点工具', keyword/catIds mutual exclusion, single-preset selection, sort field mappings, and decimal vs percent conventions. However, it does not explicitly state when to prefer mall_search over temu_goods_search/review_search, so alternative tool selection is only partially covered.

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

• temu_site_listA
  4.7/5.0
  Behavior4/5

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

  With no annotations, the description carries the full burden. It discloses matching behavior ('精确匹配，不按语言、币种或相似名称猜测'), ambiguity handling ('无匹配或多个匹配时请用户确认'), and how to interpret the returned currency. It does not explicitly state read-only or pagination, but the core behavioral traits are well covered.

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

  Conciseness5/5

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

  The description is dense but every sentence earns its place: purpose, usage conditions, matching logic, and result usage. It's front-loaded with the primary purpose and avoids redundancy despite its length.

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

  Completeness5/5

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

  For a single-parameter lookup tool with an output schema, the description fully covers when to call, what to pass, how to handle ambiguity, and how to consume the result. It leaves no significant gaps for the agent to invoke correctly.

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

  Parameters4/5

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

  The schema has one parameter with no description (0% coverage). The description compensates by explaining the parameter's meaning: 'country 使用用户给出的中文名或英文名做精确匹配' and that it is optional with a default fallback to site ID 48. This adds essential semantics beyond the schema.

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

  Purpose5/5

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

  The description clearly states the tool's function with a specific verb ('实时查询' - real-time query) and resources (Temu country sites, site IDs, internal region IDs, currency). It also distinguishes itself from sibling search tools by being a site lookup, and even provides explicit exclusions (US site, no site specified), reinforcing its unique purpose.

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

  Usage Guidelines5/5

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

  The description explicitly states when to call: '仅当用户明确指定美国以外的国家或地区时调用' and when not to call: '未指定站点或指定美国站时直接让业务工具使用默认站点 ID 48'. It also instructs how to use the result in other tools (商品、图搜、店铺、类目、关键词或评论查询), providing clear context and alternatives.

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

• temu_category_searchA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden and delivers extensively. It discloses defaults (US site 48), fuzzy search behavior, sorting conventions (totalSold/dsr), interpretation caveats (blue-ocean index must be cross-validated, period fields are deltas and may be negative, growth rates use decimals), pagination sampling, and a strict linkUrl display rule. This goes far beyond a simple read/write hint.

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

  Conciseness4/5

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

  The description is long but dense, with every sentence carrying meaningful operational guidance. It is appropriately sized for the tool's complexity, though a bulleted or sectioned format could improve scannability. The front-loaded purpose sentence ensures quick orientation.

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

  Completeness5/5

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

  Despite no annotations and a top-level schema with no description, this description is highly complete. It covers site selection, search strategy, sorting logic, data validation, pagination caveats, and output display requirements. The presence of an output schema means return values need not be documented, and this description fills all other important gaps.

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

  Parameters4/5

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

  Schema description coverage is reported as 0% at the top level, so the description must compensate. It does explain key semantics for several parameters: parentCatId only when trusted, sorting fields (totalSold, dsr, monthSoldRate, monthSalesRate), the decimal format for rates, and negative values for count deltas. While it does not enumerate every filter, it provides essential usage guidance for the most consequential fields, though a bit more explicit mapping to parameter names would be ideal.

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

  Purpose5/5

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

  The description clearly states the tool searches Temu category names, category levels, or direct subcategories, and explicitly lists its purposes: obtaining credible category IDs, confirming full paths, and researching market capacity, demand growth, supply, and entry opportunities. It also distinguishes itself from sibling tools by mentioning that trusted IDs can be passed to goods, mall, or keyword tools, and that other countries require the site tool first.

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

  Usage Guidelines5/5

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

  The description gives explicit when-to-use guidance: for category research and ID retrieval, with specific alternative instructions (e.g., 'other countries first call the site tool'). It also provides exclusion criteria, such as not restricting to level 3/4 unless the user requests, and not guessing parentCatId, which clarifies how to use the tool correctly versus other search tools.

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

• temu_goods_searchA
  4.8/5.0
  Behavior5/5

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

  No annotations are provided, so the description carries the full transparency burden. It discloses key behaviors: default site behavior, page maximum of 200, sample labeling when not fully paged, interpretation of inventory 0 as 'not counted', requirement to use server linkUrl for product links, and competition thresholds for similarNum. These go beyond simple read/write hints and are highly actionable.

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

  Conciseness4/5

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

  The description is long but information-dense; every sentence carries operational value. However, it is a single block of text without visual structure (bullets or sections), making it less scannable for an agent. Still, it is appropriately sized for the tool's complexity and each statement earns its place.

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

  Completeness5/5

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

  Given the large schema and no annotations, the description is remarkably complete: it covers default site behavior, sorting conventions, preset recipes, output link formatting, pagination/sampling, inventory caveats, and when to delegate to other tools. It gives an agent enough context to select and invoke the tool correctly for a wide range of product research tasks.

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

  Parameters4/5

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

  The single top-level `query` parameter has 0% schema coverage per context, so the description must compensate. It does so by explaining how to select between keyword and catIds, which sort fields map to specific intents (daySold for hot sellers, onSaleTime for new products), and how to combine filter ranges for low-competition or new-store presets. It doesn't enumerate every min/max field but provides the critical semantic recipes beyond raw schema.

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

  Purpose5/5

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

  The description opens with '搜索和筛选 Temu 商品' (search and filter Temu products) and enumerates concrete use cases (hot sellers, daily rankings, new products, low competition, new store products, big seller new products, price ranges, competitors) plus analysis fields. This clearly identifies the tool's verb+resource and distinguishes it from sibling tools like mall search or image search.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance: default site 48 and call site tool for other countries; choose keyword vs catIds based on intent; defines preset criteria (e.g., low-competition requires sold≥100, similarNum 1-10, sort by daySold); and explicitly says to call review search only when review evidence affects decisions. This is strong usage direction with alternatives.

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

• temu_image_searchA
  4.8/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden. It discloses critical behaviors: default image-similarity ordering, intersection semantics of image and conditions, pagination strategy (200 per page, same conditions until full coverage), sample vs. complete-hits distinction, no-result handling and image suggestions, plus the requirement to use linkUrl for clickable product names. These go well beyond basic operation and prepare the agent for realistic edge cases.

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

  Conciseness4/5

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

  The description is long but densely packed with essential rules, each sentence serving a distinct purpose (function, usage guardrail, sort semantics, return structure, pagination, no-result handling, link presentation). It is front-loaded with the core purpose and then elaborates. It could be seen as verbose, but given the tool's complexity and the many behavioral constraints, the length is justified and no sentence is redundant.

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

  Completeness5/5

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

  The description comprehensively covers the tool's complex behavior: input types, filter intersection, sort rules, pagination for full analysis, sampling distinction, no-result fallback, and link display. An output schema exists, so not detailing return fields is acceptable. The description leaves no major operational gap for an agent deciding when and how to use the tool correctly.

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

  Parameters4/5

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

  Schema description coverage is reported as 0% at the top level, so the description must compensate. It lists the major filter dimensions (site, keyword, category, sales, price, supply price, rating, review count, inventory, similar count, hosting mode, time, sort, pagination) and explains the image input formats (local path, URL, Data URI, Base64) plus sort default behavior. While it does not enumerate each individual min/max parameter, it provides sufficient conceptual context and points to the schema's nested property descriptions, adding value beyond the bare schema.

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

  Purpose5/5

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

  The description explicitly states the action: '用用户上传的商品图、实拍图、供应商图、网页图片、Data URI 或 Base64 图片搜索 Temu 视觉同款' (search Temu visual similar items using user-provided images). It clearly distinguishes from sibling tools by emphasizing image-based retrieval and noting it overlays the same filters as product search, making the purpose specific and non-confusable with keyword or mall search.

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

  Usage Guidelines5/5

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

  The description gives explicit when-to-use and when-not-to-use guidance: '用户要求以图找同款时必须以图片为主检索依据...不先主观描述图片并改用关键词冒充' and '无结果时...不能用普通关键词结果替代'. It also explains when to apply different sorts (hot, low price, new, low competition) within visual candidates, providing clear decision rules for the agent.

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

• temu_keyword_searchA
  4.9/5.0
  Behavior5/5

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

  With no annotations provided, the description carries the full burden of behavioral disclosure, and it excels. It clarifies the semantics of firstOnSaleTime ('表示该词下最早商品的上架时间，不是关键词创建时间'), warns that blue ocean index alone is insufficient ('不能单独作为进入依据'), explains that product/store count period fields are change amounts that may be negative, and that growth rates are decimals. It also covers pagination fidelity ('分页未完成时标为样本') and output binding requirements. This goes far beyond what the schema describes.

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

  Conciseness4/5

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

  The description is a single dense paragraph of about 300 Chinese characters. Every sentence adds a distinct piece of guidance—use cases, sort conventions, semantic caveats, and output requirements—so there is no filler. It could be improved by splitting into sections or bullet points for readability, but the content is efficient and front-loaded with the primary purpose.

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

  Completeness5/5

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

  Given the tool's high complexity (dozens of parameters, multiple scenarios, nuanced field semantics), the description is remarkably complete. It covers site defaults, parameter selection heuristics, sorting for each use case, interpretation pitfalls, pagination handling, and linkUrl binding. An output schema exists, so return values need no description; the behavioral notes fill all critical gaps.

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

  Parameters5/5

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

  Schema description coverage is 0%, so the description must compensate, and it does thoroughly. It explains the purpose of keyword vs catIds, sets siteId default to 48 and defers other sites to the site tool, maps sort values to scenarios (totalSold for hot, dsr for blue ocean, firstOnSaleTime for new, monthSoldRate/monthSalesRate for growth), and clarifies interpretations for dsr, product/store counts, and rate decimals. It also prohibits self-translating user input, adding semantics beyond the schema fields.

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

  Purpose5/5

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

  The description opens with the specific verb and resource: '搜索 Temu 中文或英文关键词' (search Temu Chinese/English keywords), and enumerates clear use cases (特定词、热销词、蓝海词、新词、需求增长和品类搜索词机会). It differentiates from sibling tools like temu_goods_search by explicitly noting that candidate keywords can be handed off to the product tool for validation. This makes the purpose unambiguous and distinct.

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

  Usage Guidelines5/5

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

  The description provides explicit when-to-use guidance: '查特定词优先 keyword' (prioritize keyword for specific terms), '做品类词挖掘优先 catIds' (prioritize catIds for category mining), sorting rules for hot/blue-ocean/new/growth scenarios, site selection defaults, and when to delegate to the site, category, or goods tools. It even states when NOT to combine parameters ('只有明确要求...才组合'). This is exemplary for guiding tool selection and parameter use.

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

• temu_review_searchA
  4.9/5.0
  Behavior5/5

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

  With no annotations provided, the description carries full burden and excels: it discloses pagination limits (200 per page, 10000 max), default sorting, the meaning of total=0, helpfulness as reference value not frequency, comment time vs collection time, and analytic caveats about not overgeneralizing.

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

  Conciseness4/5

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

  The description is very long and dense, but every clause carries practical value, covering operational limits and analytical warnings. It is somewhat unstructured as a single block, but not wasteful; a slight structure improvement would make it perfect.

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

  Completeness5/5

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

  Given the tool's complexity and the presence of an output schema, the description covers usage limits, pagination, data interpretation caveats, and output handling (Chinese column names, preserving nulls). It is complete enough for correct invocation and result interpretation.

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

  Parameters5/5

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

  Schema coverage is reported as 0%, so the description compensates by explaining how to use filters (e.g., score ranges for different purposes, helpful sorting, SKU grouping) and pagination strategy. It adds strategic meaning beyond the schema's structural definitions.

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

  Purpose5/5

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

  The description clearly states the tool queries real reviews for a specific Temu product ID, listing filtering and sorting capabilities. It explicitly distinguishes itself from whole-site product search, which differentiates it from sibling search tools.

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

  Usage Guidelines5/5

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

  It gives explicit when-to-use guidance (analyzing purchase motives, use cases, positive/negative aspects, etc.) and when-not-to-use (not for whole-site product search), directing users to product search first if no ID is available. It also provides tactical advice on sorting and filtering.

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