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

Goes well beyond the readOnlyHint/openWorldHint annotations by declaring the audit is static and never executes user code, describing the finding payload (severity, file:line or policy, evidence, exact fix pattern, fingerprint), and disclosing the gating relationship with build_go_live. No behavior contradicts the annotations.

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 purpose and a distinct-sibling claim, then findings taxonomy, then the fix/re-run workflow — a sound ordering with no filler sentences. It is a single dense paragraph that runs long, which slightly hurts scannability, but every clause carries information.

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 takes on the burden and delivers: it enumerates the finding shape, the severity vocabulary, and the blocking semantics. Combined with full schema coverage and read-only annotations, an agent has everything needed to call it and act on results.

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 the schema already carries per-parameter meaning, but the description adds the selection logic that the schema doesn't express — files vs. files_ref vs. project_uuid, and the project_uuid-only path auditing the latest published (or version_uuid) bundle. It doesn't add format details for files_b64gz or min_severity 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?

States a specific verb and resource ('SECURITY + CORRECTNESS AUDIT of a bundle') plus scope ('BEFORE go-live') and mode ('static; your code is never executed'). It explicitly separates itself from build_validate and build_doctor by naming what those tools miss (MONEY-01, AUTHZ-01, FLOW-01, INV-01, PUB-01, LAUNCH-01).

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 routing against siblings ('finds what build_validate/build_doctor do not'), the operating sequence ('fix every blocker and critical, then re-run until clean'), and the downstream consequence ('build_go_live reports or, when enforced, refuses on outstanding blocker/critical findings'). It also states the two invocation modes: pass files/files_ref, or only project_uuid.

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