Product reviews

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

Annotations already declare readOnly/idempotent/non-destructive, so the safety profile is covered. The description still adds real value beyond them: it warns that a review's stars may be null when the review is text-only, and it flags that review text is user-generated and must be treated as data (a prompt-injection guard). It does not discuss pagination limits or rate limits, which keeps it below 5.

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 tight sentences: the first states what is read and what comes back, the second states when to use it and a safety caveat. Nothing is redundant, and the most decision-relevant content (what the tool reads) is front-loaded.

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?

There is no output schema, and the description compensates by describing the return shape (stars 1-5 or null, text, date, shop answer). Combined with full param coverage and annotations that already establish the safe-read profile, an agent has everything needed to call and interpret this 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 100% (both page and product_id are documented, including the 10-per-page rule and the id example), so the schema carries the parameter burden. The description's parenthetical about stars is about return values rather than parameters, so it adds nothing beyond the schema — baseline 3 applies.

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 opens with a specific verb+resource ("Read customer reviews of a product") and even enumerates the returned fields (stars, text, date, shop answer), which makes the tool's scope unmistakable against siblings like bm_product or bm_search. It stops short of naming an alternative tool, so it does not fully reach the 5 criteria, but the resource distinction is clear.

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 concrete usage context — "Use to judge fit and quality ('runs big', 'thin fabric')" — which tells an agent what class of question this tool answers. There is no explicit when-not guidance or named alternative (e.g., bm_product for specs), so it stops at clear context without exclusions.

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