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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered structurally. The description adds the genuinely useful boundary that only unsent mail in specific states can be withdrawn, though it omits what happens to the underlying outreach record and whether the cancellation is reversible.

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?

One sentence, front-loaded with the action and immediately qualified by the eligibility states. Nothing is padded and no sentence is wasted.

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 and no annotations on outcomes, the description covers eligibility but not the post-cancellation state of the outreach record, error behavior when the mail has already sent, or the role of the reason parameter. Adequate but leaves real gaps.

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 0% and the description mentions neither outreach_id nor reason. With two undocumented parameters, the description does not compensate for the coverage gap; only the implied object of "an e-mail" hints at outreach_id, and the optional reason field is never explained.

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 ("withdraw") and resource ("an e-mail") and enumerates the eligible states (pending_approval, approved, failed, queued), which lets an agent separate this from approve_message, reject_message and send_email without opening any schema. It never names a sibling explicitly, so it stops short of a 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?

The condition for use is stated precisely: the e-mail must not have gone out yet, with the qualifying states listed. It gives clear context for when the tool applies but names no alternative (e.g. reject_message for declining an approval) or explicit when-not-to-use case.

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