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

Annotations already declare destructive/idempotent/not-read-only, yet the description adds real behavioral context: the exact effect ('never reaches LinkedIn'), the refusal condition, the error code comment_not_cancellable, and explicit guidance not to retry. That is disclosure well beyond the annotation set.

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 front-loaded sentences: purpose, then return shape, then error semantics. No filler; each sentence carries distinct, load-bearing information.

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 mutation with annotations and an output schema, this covers purpose, side effects, return shape, and terminal error handling with user-facing guidance. Nothing needed to invoke or interpret it correctly 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 coverage is 100% and the single parameter is fully described there ('The id of the committed comment draft to cancel'). The description reinforces the 'committed' state requirement but adds no syntax or format detail beyond the schema, so 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+resource with scope: 'Cancel a committed comment before it is sent, so it never reaches LinkedIn.' The state qualifier ('committed') implicitly separates it from draft-creation/delete siblings, but no sibling is named, so it stops short of a clean 5.

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?

Clearly conveys when to use it (a committed comment not yet sent) and what happens in every failure state ('never committed, is posted, failed or cancelled, or is being sent is refused'). It even tells the agent to stop retrying, but it never names an alternative tool (e.g., delete_draft) for the non-committed case.

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