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

Beyond the destructiveHint annotation, the description discloses that the operation destroys/discards a launch approval and clarifies there is 'No Meta write', meaning the destructive effect is local to the approval record. It also surfaces a failure mode ('stale plan digest is rejected'), adding useful runtime context.

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 short sentences, each carrying distinct information: what the tool does, when to use it, and the key alternative/side-effect. No filler or redundant restatement of the schema.

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?

Given the output schema exists and the annotations already flag destructiveness, the description covers the remaining decision-relevant context: source of inputs, recovery-path trigger, external-write behavior, and the alternative tool. An agent has enough to invoke it correctly.

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?

The description names both required parameters and tells the agent they come from operations_get_approval, which is valuable because schema coverage is 0%. The 'stale plan digest is rejected' clause adds semantic meaning to expected_plan_digest, though the description relies on the schema for exact format details.

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 opens with a specific action ('Discard a launch approval') and names the exact identifying inputs (approval_ref, expected_plan_digest) and their source (operations_get_approval). It also distinguishes this tool from launch_deny, so an agent can select it correctly.

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?

Explicitly states the recovery-path use case ('when the raw confirm_token is unavailable') and names the alternative ('Use launch_deny when you have the token'). It also gives a behavioral precondition: a stale plan digest is rejected.

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