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

Annotations already declare destructive=true, readOnly=false, idempotent=true. The description adds genuinely useful context beyond that: the auth requirement ('Requires the organization API key') and the capability constraint ('Your key cannot approve, only cancel'), plus the distinction between withdrawing a request versus revoking an unused approval.

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 tight sentences, front-loaded with the core action and the parenthetical nuance, then the key constraint. No filler or redundancy.

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 single-parameter destructive mutation with no output schema, the description covers the operation, the auth requirement, and the key's inability to approve. It is nearly complete; a note on irreversibility or post-cancel state would close the remaining gap, though destructiveHint already signals the risk.

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 and schema description coverage is 100% ('apr_... ID' is documented in the schema), so the schema carries the burden. The description adds no format or syntax detail for approval_id, making this a 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 ('Withdraw an approval request (or revoke an approval not yet used)') and clarifies the dual semantic of cancel vs revoke. It does not explicitly name a sibling alternative, but the action is unambiguous enough that an agent can distinguish it from approval_* readers like approval_status.

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?

Usage is implied by the action (withdraw/revoke a pending or unused approval) and the constraint 'Your key cannot approve, only cancel' narrows the intent. However, no explicit when-not condition or named alternative (e.g. how to approve instead) is provided, leaving routing partly to inference.

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