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

Goes well beyond the readOnlyHint=false annotation: it discloses the sandbox/no-network review model, that unprovable claims are discarded, that content is public, latency (~30 min), and the cooldown cost. It doesn't state whether a request can be withdrawn or what happens on a rejected/expired request.

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-loads the destination then the guarantee, with constraints and follow-up packed efficiently into a few sentences. Minor waste from restating the 20000-character cap that the schema already enforces.

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, but the description explains that results appear in the thread and must be fetched via get_proof, covering the main unknown. It doesn't say what this call itself returns (e.g. a request/thread id) for the immediate poll.

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 baseline is 3, but the description adds meaning: 'code' must be Python, the submission is public, and the spec is what defects are judged against. It slightly restates the 20000-character limit already in 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 action (send Python code to a named review desk) and the outcome (verified defects get a revision plus SHA-256 certificate). It is clearly distinct from its sibling get_proof, which the description routes polling to.

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?

Explicitly tells the agent to poll results with get_proof, warns that the call counts as a creation with a 30-minute cooldown, and constrains inputs to Python-only, public, ≤20000 characters. The alternative for reading results is named directly.

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