Verify Endorsement

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

Annotations already cover safety (readOnly, idempotent, non-destructive), and the description goes well beyond them by disclosing the security boundary of the result: signature validity is proven, key-to-principal binding is explicitly not. That prevents the agent from over-trusting a 'valid' outcome.

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 tight sentences, action first, then the positive guarantee, then the negative boundary. No filler and nothing redundant.

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 one-parameter verification tool with no output schema, the description supplies exactly what is needed: what a positive result means and its limits. Nothing an agent needs to interpret the result 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?

Schema description coverage is 100% for the single endorsement_id parameter, so the schema already carries the parameter's meaning. The description's reference to principalPublicKey describes the endorsement's contents, not the input, so it adds nothing beyond the schema baseline.

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 precise verb and object ('Check an endorsement's signature') plus the exact key it checks against, which cleanly separates it from sibling verification tools like verify_delegation, verify_issuer, and verify_charter.

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?

The 'what a valid result establishes / does not establish' framing tells the agent when this tool is sufficient and when it is not (when a trust anchor is required), which is strong conditional guidance. It stops short of naming a specific alternative sibling to use in the out-of-band case.

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