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

Goes well past the annotations (destructiveHint=true, idempotentHint=false): it names the concrete destructive consequence — setting visibility to private revokes public access — and adds an authorization constraint that only the owner's own session can change visibility, not a job run. It also states the mutual-exclusivity rule of one change kind per call, which is behavioral context no annotation provides.

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?

Four dense sentences with no filler, front-loaded on the primary update action before the vote/comment modes. The mid-paragraph pivot to 'Or leave feedback on an accessible proof' slightly disrupts the flow and reads as an afterthought, but nothing 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 10-parameter, destructive, multi-mode mutation with an output schema and full schema coverage, the description supplies exactly the missing pieces: destructive consequence, permission gate, per-call exclusivity, and self-vote permission. Return values are covered by the output schema, so no further explanation is needed.

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; the description earns above that by adding semantics the schema lacks — that metadata, vote, and comment are mutually exclusive per call, and that owners may vote on their own proofs. It leaves disclosePortableProof, walletAddress, and parentId unmentioned, so it does not fully cover the 10-parameter surface.

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 (update) and resource (a proof you own) and enumerates the mutable fields: title, tags, visibility. It also discloses the secondary modes (vote, comment) that the same endpoint handles, so an agent knows this is a multi-purpose mutation rather than a pure metadata edit, distinguishing it from proofs_get and proof_revoke.

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 concrete when-to guidance: confirm before making an already-shared proof private, send only one kind of change per call (metadata, vote, or comment), and delegated agents need manage_proofs. It never names a sibling alternative (e.g. proof_revoke for revocation), so it stops short of the top tier, but the exclusions and prerequisites are explicit.

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