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

Annotations already declare a safe, idempotent, non-destructive read, so the description correctly focuses elsewhere: per-call pricing (¥0.2/次), billing only on success with automatic refunds for failures or empty results, and the upstream pagination ceiling. Those cost and depth constraints are genuinely decision-relevant and not derivable from annotations. It stops short of describing rate limits or latency.

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 in a deliberate order: what it returns, when to use it, what it costs, how deep it goes. No filler and no repetition of the title or schema.

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?

With no output schema, the description must state the return payload and does so field by field. Combined with cost behavior and pagination limits, an agent has everything needed to decide to call it and to interpret the result.

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 coverage is 100%, so item_id, seller_nick, page and _token are already documented in the schema. The description adds only that results are paged ('按页返回'), without explaining page semantics, max depth, or whether seller_nick disambiguates the item.

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 first sentence gives a specific verb and resource ('获取1688商品评论') and then enumerates the returned fields (评论正文、点赞数、回复数、评论者昵称与地区、时间戳), so an agent knows exactly what it gets. It differentiates accurately by platform, though it never explicitly positions itself against the website's many other *_comments siblings.

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?

'做评论情感分析、竞品口碑对比或舆情监测时用' names three concrete downstream scenarios that select this tool, and the closing sentence bounds pagination depth so an agent knows when to stop. There are no explicit exclusions or named alternative tools for when this is the wrong choice.

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