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

Adds substantial behavior beyond the annotations: moderation rules (pending if the review holds links or the account is under a day old), a rate limit (one edit an hour), version retention, a thank-you email side effect, cost (free), and auth requirements. Annotations only say non-read-only, destructive, non-idempotent, open-world; the description supplies the operational detail an agent actually needs.

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?

Front-loads purpose and replacement semantics, then adds constraints and side effects in short clauses. Dense but mostly waste-free; the semicolon-chained delivery of free/auth/rate-limit details is slightly run-on, though each fact earns its place.

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?

Covers the high-risk aspects for a 9-parameter public mutation: moderation outcome, rate limit, auth, versioning, and side effects. No output schema exists, so an agent may still be unsure what the response contains (e.g., published vs pending status, review identifier), which is the main remaining gap.

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 field meanings and limits are already documented in the schema. The description loosely maps the content fields ("1–5 stars, what they like and dislike, what they use it for") and adds the constraint that values must come from the human, but it does not explain display_name defaults or marketing_consent beyond the schema.

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?

Names a specific verb and resource ("Posts the human's public review of Geocode AI") and immediately discloses the upsert semantics ("or replaces their existing one; each account has one review"). This distinguishes it from siblings like get_my_review and list_reviews, which read rather than write.

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 a clear constraint on when/how to call it: "Only call it with the human's own rating and words, never invented ones." It stops short of naming alternatives (e.g., get_my_review to inspect an existing review before editing) or stating when not to call, but the context is unambiguous.

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