category.recommend

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

With no annotations, the description carries the full burden. It discloses that this is an AI inference operation returning catId/catName and suggests no side effects, but it does not mention limitations, failure modes, or the fact that images_json is optional.

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 one compact, front-loaded sentence with minimal filler; it states the core behavior and result. It loses a point only because 'AI' is slightly generic and the input/output are compressed into a telegraphic phrase.

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 output schema removes the need to document return values, and the input schema covers requiredness, so the description is adequate for a simple tool. However, the 'title+image' phrasing could mislead an agent about the optionality of images_json, and no broader usage context is given.

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. It links 'title' to 标题 and 'images_json' to 图片 and adds product context, but it does not clarify the expected JSON format or that images are optional, so compensation is only partial.

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 names a specific operation ('AI 识别商品类目' — recognize product category) and the exact result (catId/catName). This distinguishes it from all listed siblings, none of which provide category classification.

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 the tool is for product-category classification from title and/or images, but it does not state explicit when-to-use or when-not-to-use conditions. Since no sibling overlaps with this function, the implied usage context is mostly sufficient.

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