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

readOnlyHint=true is already supplied, so the safety profile is given; the description still adds real behavior context by stating it deliberately omits the review list to save tokens. What it does not disclose is cost/latency or whether the distribution is bucketed per star, but for a read-only aggregate the disclosure is well above the annotation floor.

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?

Two short clauses: the payload and its token-saving purpose are front-loaded, then the sibling routing comes last. Every phrase earns its place with no restatement of the title.

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 one-parameter read tool with no output schema, the description covers the return contents (average, distribution, total) and the exclusion, which is enough to call it correctly. Minor gap: the shape of the 分布 (per-star buckets vs. other) is left implicit.

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?

The single parameter productId has 100% schema coverage including the cuid format hint. The description refers to '某产品' but adds no further meaning about the identifier or its resolution, so it neither helps nor hurts beyond the schema baseline.

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 verb and resource (只取某产品的星级汇总) and enumerates exactly what the payload contains: 平均分 + 分布 + 总数. It also explicitly contrasts with the sibling get_product_ratings, so an agent can distinguish the two without opening either schema.

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 gives both the positive trigger (省 token 的「评分多少」快查) and the negative case with the named alternative (要看评价文字用 get_product_ratings). This is explicit when/when-not guidance with a sibling pointer, not mere inference.

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