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

Annotations already declare destructiveHint=true and idempotentHint=true. The description adds real context beyond them: it specifies what is destroyed (the unused invitation link) and draws a scope boundary (accepted memberships are untouched), which is useful for a destructive mutation.

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 tight sentences, front-loaded with the action and its effect, then the precondition, then the scope exclusion. No filler.

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, idempotent mutation with no output schema, the description covers the effect, authorization requirement, and boundary case. Return behavior is unnecessary here, though a note on conflict/revision-mismatch handling would complete it.

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 67%: idempotencyKey and expectedRevision carry their own explanations, while invitationId is undocumented. The description implicitly reinforces expectedRevision semantics ('exact current invitation revision') but adds no syntax or lookup detail for invitationId, so the schema still does most of the work.

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 (revoke) and resource (workspace invitation) with scoping precision ('exact current invitation revision', 'invalidate its unused link'). It also disambiguates from the accepted-membership case, so the agent can distinguish it from sibling invitation tools like send_workspace_invitation.

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?

'Owner/admin only' gives an explicit authorization precondition, and the note about accepted memberships tells the agent when this tool does not apply. It stops short of naming a concrete alternative (e.g. removing a member) if the invitation was already accepted, so it is clear but not fully routing.

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