Cancel email

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

Annotations already declare destructiveHint=true, idempotentHint=true and readOnlyHint=false, so the safety profile is covered. The description adds real value beyond that by disclosing the failure mode and error identifier (cannot_cancel) and the state transition that triggers it, which is exactly the kind of context annotations cannot carry.

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 short sentences, front-loaded with the action and followed by the failure condition. No filler, no repetition of the title.

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 single-parameter mutation with no output schema and full annotation coverage, the definition supplies the essential precondition and error behavior. It could add whether a successful cancellation is reversible or whether the sender is notified, but nothing critical for correct invocation 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?

Only one parameter, and the schema documents it at 100% coverage with format hint (msg_…). The description adds nothing about the id, so the baseline of 3 applies — the schema does all the work here.

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?

Specific verb+resource ("Cancel a queued or scheduled email") with a scoping constraint ("before it is sent") that implicitly separates it from send_email and the read siblings. It stops short of naming an alternative explicitly, so it is clear but not fully sibling-differentiated.

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 a concrete precondition and a when-not condition: fails with cannot_cancel once delivery has started. That tells an agent when the call is valid and when it will not work, though it does not point to any alternative tool for already-sent mail.

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