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

Annotations already declare readOnlyHint, idempotentHint, and destructiveHint=false, so the description wisely avoids repeating those. It adds genuine behavioral detail: rows are hash-only, chained, citeable, and empty results are permitted. It also signals that self-lookup requires proof, which goes beyond the annotation layer. No contradiction exists.

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 short sentences, each with a distinct job: endpoint and access modes, output characteristics, and empty-result behavior. There is no filler, no repetition of schema details, and the most decision-relevant information is front-loaded.

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 read-only lookup with a rich input schema, an output schema, and strong annotations, this description is sufficient. It covers both access modes, the sensitive nature of the data ('hash-only'), the chaining/citability property, and empty handling. The authentication mechanics are already well documented in the parameter descriptions, so nothing critical is missing.

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?

The schema leaves `did` undocumented, and the description fills that gap by stating that did selects any citizen's history while omitting did plus proof selects your own. It also frames the various credential fields as collectively constituting 'proof', tying together nonce, controller_signature, controller_public_key, and leave_token in a way the schema alone does not.

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 opens with the exact endpoint ('GET /api/seal') and a specific, scoped purpose: retrieving any citizen's public seal history by did, or the caller's own history with proof and no did. It distinguishes the public and self-service modes clearly, and the 'Hash-only rows, chained, citeable' clause adds useful conceptual grounding.

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 gives concrete invocation contexts: pass a did for another citizen's public history, or omit did and supply proof for your own history. It also notes that empty results are allowed. It does not explicitly name sibling alternatives or say when not to use this tool, but the triggering scenarios are clear enough for an agent to route to it.

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