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

Annotations establish non-read-only, idempotent, non-destructive, closed-world behavior, and the description adds genuinely new context: cryptographic verification is required, the decision must be 'allow', and a record is single-use. It does not describe success/failure responses or error handling, so it adds value without being exhaustive.

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 action and the backing artifact, then the acceptance constraints. No sentence is redundant and nothing is buried.

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 mutation tool with no output schema, the definition covers the critical acceptance conditions and the crypto requirement. What remains unstated is the outcome of a submission (confirmation, storage, rejection behavior), which is a modest gap rather than a blocking one.

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 description coverage is only 20%, so the description must compensate, and it does for the hardest parameter: 'receipt' is characterized as a signed decision record in Cedulon format whose signature must verify under 'operatorKeyPem'. Server, verdict (enum), and note are left to the schema, which is largely self-explanatory for those fields.

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 — filing a report about a catalog server's state (works/broken/unsafe) — and immediately names the artifact that backs it (a signed decision record). This is clearly distinguishable from the read-only siblings get_tool and search_tools.

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 explicit preconditions: the record must verify under the supplied public key, its decision must be 'allow', and each record can back only one report. 'Unsigned opinions are not accepted here' rules out an obvious wrong approach. It stops short of naming an alternative tool, but no sibling performs a comparable action.

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