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

Annotations already declare destructiveHint=true and idempotentHint=true, and the description adds genuinely new behavior: the admin-only authorization requirement, that queued delivery is cancelled, and the important nuance that an already-submitted provider message cannot be recalled though its link stops granting membership. That partial-irreversibility detail is exactly the kind of context annotations cannot 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?

Three tight sentences with the authorization constraint front-loaded and the destructive caveat last. Every clause earns its place; 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 mutation with annotations covering safety and no output schema, the description is largely complete: it explains the action, the admin gate, and the delivery nuance. The remaining gap is that the two UUID parameters are undocumented, though their names make intent inferable.

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 only 33% — only 'confirm' is documented, and workspace_id/invitation_id carry format/pattern but no prose. The description mentions 'pending invitation' but adds no meaning about what the two UUID parameters identify, so it fails to compensate for the coverage gap.

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?

Specific verb ('invalidate') plus resource ('pending invitation') with added scope ('cancel queued delivery'). An agent can distinguish this from resend_workspace_invitation, invite_workspace_members, and remove_workspace_member 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?

'Admin only' supplies a clear prerequisite, which is more than most definitions offer. However, it never states when to choose this over resend_workspace_invitation or remove_workspace_member, so the when-not/alternatives guidance is implied rather than explicit.

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