temu_image_search

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.

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.

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.

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.

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.

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.