temu_keyword_search

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.

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.

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.

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.

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.

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.