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

Annotations declare a non-read-only, non-idempotent, non-destructive write, and the description adds real behavioral context: answers are keyed by question key, and the review keeps waiting after submission rather than completing. It does not say what happens to unrecognized keys, whether re-submission overwrites prior answers, or whether partial answers are accepted — gaps that matter given idempotentHint=false.

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?

Dense but front-loaded: the action and its precondition come first, then format rules, then the anti-guessing rule. 'Then carry on waiting for the review' is slightly ambiguous phrasing but conveys a useful fact. No filler sentences.

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?

An output schema exists, so return values need no explanation, and the nested answers object is largely self-documenting via enums. The remaining gap is submission semantics — which question keys are expected, whether unanswered questions block submission — which the description leaves implicit for a mutation tool.

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%, so the description must carry meaning, and it does for the two hardest fields: dates are YYYY-MM-DD and territory means where the home is or where the user mainly works, with the four GB-* codes spelled out. It also explains the answers object is keyed by the review's question keys. It adds nothing about rent, documentKind, or the reviewId token format.

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 concrete verb and resource — supply the facts a review asked for — and pins the exact precondition (status was needs-answers). That condition distinguishes it cleanly from get_contract_review (inspect) and start_contract_review (initiate), so an agent can route without opening sibling schemas.

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 trigger (only when the review's status was needs-answers) and an explicit constraint against fabrication ('Use only what the user says: never guess an answer'). It does not name an alternative tool to use when the status is not needs-answers, which keeps it short of a 5.

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