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

Annotations already cover the safe-read profile, but the description adds real context: verification is public (no auth), fully offline/deterministic, and the keys come back in the answer plus a published JWKS URL. It also clarifies that supplying a statement performs no read. The shape of the returned verdict itself is only implied, not stated.

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?

The core question is front-loaded in the first clause, followed by the signature/key specifics and then the input alternatives. It is dense with domain jargon ('the door's signature', 'home node') but no sentence is filler.

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 no output schema, the description still manages to say the keys are included in the answer and where to get them offline. What is missing is an explicit statement of the return verdict (valid/invalid per signature) and error behavior when a signature fails, which for a verification tool is the one lingering gap.

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 67% and 'version' has no description at all, but the text adds meaning the schema cannot: with zero required params, it tells the agent the two valid input shapes (statement alone, or subject+version) and that supplying the statement avoids any read. It does not explain what version means semantically beyond the pairing.

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 ('whether a stored statement's two signatures verify against the published keys') and immediately names the two artifacts checked (sig, node_sig) with their key ids. This is clearly distinguishable from the sibling read tools (get_target_market, get_record) which fetch rather than verify.

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?

'Give the statement itself (nothing is read) or subject and version' gives concrete invocation patterns and clarifies a non-obvious mutual alternative. It stops short of naming when to prefer this over a sibling or when verification is required, so it is clear context without explicit exclusions.

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