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

Annotations already declare a non-read-only, non-idempotent, open-world write, so the safety profile is covered. The description adds genuinely new behavioral facts the annotations do not contain: the three-way outcome contract with what each returns, the upload-URL-per-screenshot flow when files are included, and a concrete rate limit of 3 accepted submissions a day per pull 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?

Three dense sentences, no filler, and the highest-value information — the return shape per outcome — is front-loaded where it matters most given the absence of an output schema. The telegraphic style is terse but every clause carries content.

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 eight parameters, a nested files object, and no output schema, the description carries the return-value burden well by spelling out all three outcome responses and the upload flow. It leaves minor gaps around re-submission semantics and what happens on rejection or validation failure, but an agent has enough to call it correctly.

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 100% and every parameter, including nested file fields, is documented inline, so the baseline is 3. The description supplements this slightly by tying outcomes to payload shapes (reason plus drafted reply for cannot_prove, one upload URL per screenshot for files), but it does not explain proofId, section, redactions, or summary beyond what the schema already states.

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?

The definition never states plainly what the action is, opening with 'Hands back what you captured' — a description of the response rather than a verb+resource. A reader can infer that it submits a captured outcome to a pull request and gets a section or reply back, but the core operation has to be inferred from field names and sibling context rather than read directly.

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?

No when-to-use guidance and no routing against nearby siblings such as start_proof, finish_proof, or submit_patch. The outcome names (proved / cannot_prove / fix_broken) and the rate limit hint at the operating context, but nothing says when this tool is the right choice over the alternatives.

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