Get Final Review

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

Annotations already declare readOnlyHint=true, idempotentHint=true and destructiveHint=false, so safety is covered. The description adds genuine behavioral context beyond that: the 404 failure mode and its likely cause, the meaning of duplicate_submitted, and the conditional semantics of base_country.eligible. Its only shortfall is that much of that detail is really return-field semantics rather than operation behavior.

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?

The payload description is front-loaded in the first sentence and every subsequent sentence adds distinct information (precondition, 404 cause, duplicate_submitted meaning, flags shape, base_country semantics). It is dense and readable, though the long run-on paragraph could be broken into labeled segments for faster scanning.

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 must carry the return contract, and it does: it enumerates the bundle sections, explains the flags entry shape (question, source, answer, reason, EEO variant), and documents two derived fields. Nothing an agent needs to call and interpret this tool is missing.

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% for the single parameter, so the description carries the burden — and it partially does by clarifying that proposal_id means a proposal id, not an application id, which is the common misuse. It adds no format, naming, or sourcing guidance beyond that disambiguation, so it compensates only in part.

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+resource (get_final_review) and immediately enumerates the bundle contents (job summary, score delta, PDF readiness, QA answers, EEO consent flag, blocked items, evidence manifest). An agent can distinguish this pre-approval review artifact from get_proposal or get_application without opening any 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?

States the precondition clearly ('Requires an existing proposal') and gives the remediation path plus the exact failure mode (404 usually means propose_application was not called, or an application id was passed instead of a proposal id). It also frames the intended consumer context ('relevant to the user's approval decision'). It stops short of naming an alternative sibling for the adjacent questions, so it is context-rich but not a full when/when-not routing statement.

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