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

Annotations already declare destructiveHint=true and readOnlyHint=false, covering the destructive nature. The description adds behavioral context by requiring explicit user confirmation, a critical safeguard. It does not detail post-cancel consequences, but the output schema and annotations fill gaps.

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?

A single sentence with no filler. The action and its prerequisite are front-loaded, making it easy to scan and understand.

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 simple cancellation tool with a destructive annotation, an output schema, and schema-level descriptions for two of three parameters, the description captures the essential safety requirement. The missing idempotencyKey details are covered in the schema, so nothing critical is absent.

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 67%; callId has no description, while confirmed and idempotencyKey do. The tool description adds meaning to confirmed by tying it to explicit user confirmation, but provides no additional clarity for callId or idempotencyKey beyond schema. This partially compensates for the coverage gap.

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 states a specific verb 'Cancel' and resource 'call', with a clear precondition ('after the user explicitly confirms the exact call'). It distinguishes this tool from all siblings, as none other performs cancellation; the action is unambiguous.

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 gives an explicit usage precondition: only use after user confirmation of the exact call. It does not mention alternatives, but no sibling offers cancellation, so the guidance is contextually sufficient. It clearly communicates when not to use (without confirmation).

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