Cancel an order

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

Annotations flag destructiveHint and readOnlyHint, but the description adds critical behavioral detail: the response body is undocumented and returned verbatim, and the cancellation may result in a pending_cancel state. This goes beyond the annotations and helps the agent understand potential asynchronous behavior and the need for verification.

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 focused sentences pack in the endpoint, optional parameter, response caveat, and verification step. Every sentence contributes new information without fluff, and the structure is front-loaded with the core action.

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 destructive, side-effect-producing tool with no output schema, the description covers the essential points: what it does, the ambiguous response, and a concrete alternative to confirm the result. This is sufficient for an agent to invoke and react appropriately.

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% with both parameters described. The description only reiterates that reason is optional, which is already evident from the required list in the schema. No additional semantic value is added beyond the schema.

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?

The description clearly states the tool cancels an existing order, with a specific verb and resource. It distinguishes from sibling tools like create_order and get_orders_state by explicitly naming the cancellation action and including the HTTP endpoint.

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 description implies usage for cancelling orders and provides clear follow-up guidance: verify the outcome with get_orders_state, expecting canceled or pending_cancel. It does not explicitly exclude alternative tools or state when not to use, but the verification step serves as practical context.

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