Get Final Review

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial semantics beyond them: what `approval_recorded` vs `eeo.consent_recorded` mean, what `duplicate_submitted=true` implies for the approval decision, what `flags` contains (question, source, answer, reason), and when `base_country.eligible` is false. That is exactly the contextual layer structured fields don't 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?

Front-loaded with the bundle contents before the field semantics, and every sentence adds information. Slightly dense/run-on in the error-handling portion, but no filler.

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?

No output schema exists, so the description carries the return-shape burden — and it does, defining the bundle's fields, error meanings, and edge-case flags. Nothing an agent needs to call this correctly and interpret the result 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 coverage is 0% for the single parameter, so the description must compensate — and it does by clarifying that proposal_id must reference an existing proposal and by warning about confusing it with an application id. It stops short of stating where to obtain a proposal id (e.g., list_proposals), so not a 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?

Opens with a specific noun bundle ('Compact final-review bundle') and enumerates its contents (job summary, match score delta, PDF readiness, QA answers, blocked/manual items, evidence manifest). An agent knows exactly what comes back. It doesn't explicitly contrast with sibling get_proposal, so sibling differentiation is only implied.

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 ('Requires an existing proposal') and interprets the failure mode: a 404 usually means propose_application wasn't called (which accepts application_id to late-link) or an application id was passed instead of a proposal id. It also frames the context as feeding the user's approval decision. No explicit 'use X instead' exclusion, hence not a 5.

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