temu_mall_search

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.

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.

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.

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.

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.

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.