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

Annotations only mark it as a write with openWorldHint, but the description adds write-once/never-edited/never-deleted semantics, one-review-per-side limits, the conflict/not_yet/forbidden failure modes, and the proof-weight/counts/why mechanics including the dual-profile same-person case. This is far more behavioral context than the annotations carry.

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?

Purpose is front-loaded and every sentence carries substantive information (constraints, error codes, proof mechanics). It is a dense single block, though, and a reader must parse several clauses to extract the key rules; a light structural break would improve scanability without losing content.

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 write tool with no output schema, the description fully compensates: it describes the reply shape (review with proof, proof_label, counts, why) and the manifest reference (reviews.proof_weights). Combined with the mutation and error semantics, an agent has everything needed to call it 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 coverage is 75%, so most parameters are already documented (note ≤500 chars, stars 1–5 whole, idempotency_key fully specified). The description reinforces the stars/note constraints and adds value by noting that `note` is the only free text and is surfaced under `_untrusted`, plus tying purchase_id to the one-review-per-side rule. It stops short of elaborating the undocumented purchase_id format, so a 4 rather than 5.

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?

States a specific verb (review) and resource (the other side of a purchase you were part of), and immediately disambiguates from siblings like replyToReview, getReviews, myReviews and reviewPayment by naming the directional roles (buyer reviews seller, seller reviews buyer). An agent can identify this tool's job without opening the 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?

Gives explicit when-to-use (you were part of the purchase), when-not (a second call is `conflict`; unverified purchase is `not_yet`; purchase you're not part of is `forbidden`), and a named alternative (reviewPayment, for no-API-key or x402-on-Base cases). This is exactly the routing information an agent needs.

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