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

Annotations already declare destructive=true, idempotent=true and openWorld=false, so the safety profile is covered. The description adds the non-obvious authorization requirement ('Owner-only') and the state constraint ('pending'), which are real behavioral facts not expressed in structured fields.

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 short sentence with the authorization constraint front-loaded and zero filler. Nothing is padded and nothing essential is buried.

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 mutation with no output schema, the description covers who can call it and which resource state it applies to, but says nothing about the effect on the invitee (e.g., is the invitation link invalidated, is a notification sent) or failure modes. Adequate, with clear gaps.

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 50% – request_id is fully documented in the schema as an idempotency UUID, while invite_id has only its UUID pattern. The description's 'by its ID' adds nothing beyond the schema, so the baseline 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 invitation') and distinguishes itself from sibling team tools like invite_team_member and remove_team_member by scoping to pending invitations rather than members. Clear, though it does not explicitly name the siblings it differs from.

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?

'pending invitation' and 'Owner-only' imply the preconditions for use, but the description never says what to do when the invitation is already accepted or expired, nor points to an alternative tool. Implied rather than explicit guidance.

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