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

Annotations declare the mutation profile (readOnlyHint=false, destructiveHint=false, idempotentHint=false), and the description adds real context beyond them: the single-change-per-call constraint, the ownership rule for voting, and the manage_proofs scope needed by delegated agents. It does not cover failure behavior when change kinds are mixed, but the additions are substantive.

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 sentences, front-loaded with the primary purpose and then the constraints; no filler or restatement of the tool name. The middle sentence packs two rules together but remains readable.

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 9-parameter multi-purpose mutation tool with an output schema, the description covers the variables an agent actually needs to choose: ownership, permission scope, and one-change-per-call. Return values are correctly left to the output schema; only edge-case error handling is unstated.

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 a constraint the schema cannot express: which parameters may be combined in one call (metadata vs vote vs comment). It also restates the visibility enum values inline, which helps an agent orient before reading 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 verb and resource ("Update a proof you own") and enumerates the mutable fields (title, tags, visibility) plus the secondary capabilities (vote, comment). An agent can separate this from proofable_proofs_get and proofable_proofs_check without opening a 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?

Gives an explicit operational rule ("Send one kind of change per call: metadata, vote, or comment") and states who may act (owners on their own proofs; delegated agents need manage_proofs). It stops short of naming an alternative tool for any of the three change kinds, so it is clear context rather than full when/when-not routing.

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