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

Annotations only declare the safety profile (readOnly=false, destructive=true, idempotent=true, openWorld=true). The description adds substantial context beyond that: the iPhone Live Activity updates, the user loses the ability to approve/reject, any wait_for_approval call returns the cancelled state, and non-pending requests are returned unchanged. This is rich side-effect disclosure that annotations alone could not convey.

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?

Front-loaded with the core action, then side effects, then the non-pending caveat, then the retry exclusion. Every sentence carries distinct information, though the closing 'Returns the approval's resulting state' is mildly redundant given an output schema exists.

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 one-parameter mutation with an output schema and full annotation coverage, the description covers purpose, side effects, edge cases (non-pending), and the retry anti-pattern. Nothing an agent needs to call it correctly 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?

Schema description coverage is 100% and the single approval_id parameter is already documented as coming from request_approval. The description adds no additional syntax or format detail beyond the schema, so the baseline of 3 applies.

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 pending approval request') and immediately scopes it to 'pending' requests, which distinguishes it from request_approval, get_approval, and wait_for_approval. An agent can tell exactly what this tool does without opening any schema.

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 explicit when-to-use ('no longer needed... agent changed plans or the operation already happened'), explicit when-not ('Do not cancel to retry; use wait_for_approval to keep waiting'), and names the sibling alternative. It also clarifies the no-op case for already-decided/timed-out/cancelled approvals, removing ambiguity about retry behavior.

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