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

Annotations already declare destructiveHint=true and the title, and the description's 'WRITE:' label is consistent with that. It does not add the behavior an agent still needs: whether the new term runs from now or from the original deadline, and whether signers are emailed as a side effect (the schema's notify_signers default of true implies an outbound notification). No contradiction with annotations.

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?

Two compact sentences, mutation flag first, resource and endpoint second. Nothing redundant and nothing 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?

With three documented parameters, no output schema, and a destructive annotation present, the minimum is met. What's still missing is the semantic effect of the call — how the new term relates to the existing deadline and whether signers get notified — which an agent needs to call this correctly in context.

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%: term's format and pattern, notify_signers' default, and sign_request_id's provenance are all documented in the schema. The description itself adds no parameter-level meaning, so the baseline 3 applies.

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 ('extend the signing term of a sign request') plus the exact API endpoint, which is unambiguous and distinct from every sibling (cancel, create, get, list, remind). It does not explicitly contrast itself with a sibling, but no sibling overlaps the action, so disambiguation is implicit.

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?

'WRITE:' signals this is a mutation rather than a read, which is a useful routing cue toward the get/list siblings for inspection. Beyond that there is no guidance on when to extend versus cancel-and-recreate, what preconditions apply (e.g. request must still be open), or any exclusions.

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