Cancel a message

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

Annotations already declare non-read-only, idempotent, non-destructive and open-world; the description adds the operationally critical fact that cancellation is only possible before provider handoff, including the scheduled/queued states where it applies. It does not describe what happens to the message record after cancellation (e.g. status set), but output schema existence lowers the burden. No contradiction with the declared hints.

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 sentences, front-loaded with the capability and the applicable states, then the failure condition. Zero filler; every clause carries a constraint the agent needs.

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?

A simple single-parameter mutation tool with annotations covering safety and an output schema covering returns; the description supplies the one thing neither provides — the pre-send eligibility rule. Only the post-cancel state is unstated.

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 (id, msg_...) and the schema documents it at 100% coverage. The description adds no format, sourcing, or behavior detail about the identifier, so the schema does all the work — baseline 3.

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 ('Cancel a message') and immediately narrows the state space to unsent/scheduled/queued messages. It implicitly separates itself from the send_* siblings but never names a counterpart or alternative tool, keeping it 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?

Gives a clear eligibility condition ('has not been sent yet, such as a scheduled one or one still queued in a batch') plus an explicit exclusion ('already handed to the provider cannot be called back'). No named alternative tool or preconditions (permissions, timing) are given, so it is clear context without full routing guidance.

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