Revoke Invitation

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

Adds real context beyond the annotations: the invitation link is invalidated, the action is recoverable (re-invite is possible), and it requires admin/owner privileges. The recoverability note is consistent with destructiveHint=false since nothing is permanently destroyed. It doesn't say whether revoking an already-accepted invitation errors out, which keeps it from a 5.

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 short sentences in descending priority: action+effect, reversibility, then prerequisite. Zero 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 one-parameter mutation with an output schema already defined, the description covers effect, reversibility, and permission gating — everything an agent needs before calling 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 100% and the single parameter already carries a description pointing at list_invitations. The description adds nothing about the id's format or failure behavior, 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 (cancel/revoke) and resource (a pending invitation) plus the observable effect: 'its link stops working.' That effect cleanly separates it from resend_invitation and invite_people without needing to name them.

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?

Scoping is explicit — it applies to a pending invitation only, and the follow-up 'can be invited again later' tells the agent this is the non-permanent path versus deactivate_member. It states the required role (workspace admin or owner) but doesn't explicitly name the sibling alternative for a different case.

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