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

Annotations already cover the safety profile (readOnly=true, idempotent=true, non-destructive, openWorld), and the description adds genuinely non-obvious behavior: ¥0.3 per call, billed only on successful calls, with failures and empty results auto-refunded. That cost/failure semantics materially affects an agent's decision to call in bulk. It stops short of saying what an empty result looks like or whether a product_id that resolves to a video is accepted.

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?

Four tight sentences, front-loaded with purpose then returns, then use cases, then billing — no filler and the pricing sentence earns its place because it changes calling behavior. The only bloat is the return-field enumeration, which occupies a full sentence while appearing inaccurate for this resource.

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 read-only single-entity fetch with no output schema, the definition supplies use cases, return shape, and cost model, which is broadly sufficient. However, the return shape is the one thing that appears wrong for a 商品 resource, so an agent cannot reliably predict what it will receive, and there is no note on what an empty/not-found response means beyond the refund promise.

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 100% across both parameters (product_id and the backup _token), so the schema already explains usage; the description adds nothing about product_id format, ID source, or whether share-links are accepted. With full schema coverage this lands at the baseline 3.

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 verb+resource ("获取抖音商品详情") is specific, but the enumerated return fields — 点赞/评论/收藏/转发数, 作者昵称与sec_uid, 封面与背景音乐 — describe a video/post payload, not a product payload (no price, sales, SKU, shop). That reads as copy-paste from douyin_video_detail and leaves an agent unsure whether this tool returns product data or content data, and no sibling is named to disambiguate.

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?

It names three scenarios (单条互动量分析, 素材入库, 批量任务起点), which is real usage context, but gives no when-not guidance and never points to alternatives such as douyin_video_detail or douyin_shop_search. The suggested scenarios are also content-analysis oriented, which is misaligned with a product-detail tool and could steer an agent into the wrong choice.

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