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

Beyond annotations (readOnlyHint=false, idempotentHint=true, destructiveHint=false), the description discloses server-side validation of uploads (type, size, metadata stripped), an expected latency (visible within a minute), and the failure response shape (missing slots returned). It doesn't cover the success return payload beyond latency, or auth/permission requirements, keeping it short of a 5.

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?

Two short sentences, with the precondition and outcome front-loaded and nothing padded. The final clause "Answers missing with the slots still to upload" is slightly telegraphic and could be phrased more plainly, but no sentence is wasted.

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?

For a one-parameter mutation step with no output schema, the description covers the precondition, the processing behavior, the latency expectation, and the error case. Only permission/auth context is absent, which is a modest gap given the annotations already flag it as non-read-only and open-world.

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?

There is a single parameter with 100% schema coverage, so the pattern and description for proofId already carry the semantics. The description adds no extra meaning about the identifier's origin or format, so the baseline 3 is appropriate.

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 description gives a specific verb and resource ("Finishes a proof") plus the precondition "once every screenshot is uploaded," which tells an agent this is the terminal step after uploads. It doesn't name sibling tools like submit_proof or start_proof, so differentiation is inferred from the ordering language rather than stated.

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?

It states a clear precondition for calling (all screenshots uploaded) and hints at a retry path by saying it "Answers missing with the slots still to upload." No explicit when-not or named alternative is given, but the operational context is unambiguous for a one-parameter step tool.

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