submit_findings

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

With no annotations, the description carries the full burden and does well: it discloses the state-machine consequences of both branches (empty list → done, non-empty → review) and that findings are created in pending_verification. It omits whether the claim is consumed/released and any error behavior for an invalid ClaimToken.

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?

Three tight sentences, front-loaded with the scope restriction and then the two branch outcomes. No filler, each sentence adds a distinct behavioral fact.

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 and no annotations, yet the description covers the important outcome of both branches, which is what an agent needs to invoke this correctly. It leaves a gap on finding payload structure and ClaimToken handling, so not fully complete for a 3-param mutation.

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 compensate. It alludes to one parameter (the findings list, and implicitly the claimed task for ClaimToken) but never explains the shape of a finding, the format or role of ClaimToken, or what as_agent does.

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+resource ('submit findings') scoped explicitly to 'the currently-claimed task' and to 'Audit-plan only', which separates it from sibling submit_* tools like submit_verification_verdict and submit_attempt_verdict. An agent can identify what it does and when it applies without opening the 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?

The 'Audit-plan only' scope and 'currently-claimed task' precondition give clear context for when this applies versus other lifecycle submits. It does not name an alternative tool or state when-not to use it, so it falls 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.