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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), yet the description still adds real value: a hard cap of twenty results, an explicit prompt-injection warning that review text is untrusted data, and a disclosure of what is deliberately omitted (shopper identity, booking identifier, provider reference). The one gap is that the 'up to twenty' cap implies no pagination without saying so or how to get more.

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?

Three tight sentences, each doing distinct work: scope first, safety warning second, return-surface limits third. Nothing repeats the schema or the annotations.

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 steps in to characterize the return set (count ceiling, excluded identifiers), which is exactly what an agent needs. It stops short of describing ordering, pagination/continuation behavior, or the review fields (rating, date) that likely come back.

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% and the single parameter business_id is never named in the description, so the agent must map 'a published business' to it themselves. That phrase does carry meaning — the business must be published/listed, not merely known — which partially compensates for the missing parameter documentation.

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?

Specific verb ('Reads') plus a precisely scoped resource ('up to twenty receipt-backed reviews of a published business'), which is far more informative than the title alone. The read-only framing implicitly separates it from the write sibling submit_verified_review, but that sibling is never named.

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?

Usage is only implied: the agent can infer this is the retrieval path for a business's reviews, but there is no statement of when to call it versus submit_verified_review or ask_business, and no prerequisites (e.g. must the caller own or have claimed the business?).

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