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

Goes beyond the destructiveHint=true annotation with genuinely useful specifics: the emailed link stops working immediately and the invitee can no longer join. The canonicality/idempotency/confirmation-boundary tail is largely generic template text rather than tool-specific behavior, which caps it below 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?

The first two sentences are well front-loaded and earn their place, but the closing boilerplate ('every prerequisite stated above', retry-key/canonicality/context_engineering language) is repetitive filler that dilutes the useful content.

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?

Covers the essential operational context for a destructive mutation: prerequisites (authenticated active company access), side effects, and a confirmation boundary. With no output schema required and side effects well stated, it is nearly complete, though parameter detail remains thin.

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?

With 0% schema description coverage, the description must carry the load; it names 'email' and 'companyId' but adds no format or semantics (valid email shape, whether companyId is optional, what _corply_context does). It partially compensates but leaves a real gap for a 3-parameter tool.

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 ('Revoke a pending company invitation') and immediately bounds scope: only pending invites, and 'accepted memberships are never undone.' This clearly separates it from siblings like redeem_invite, invite_member, and invite_cofounders without opening their schemas.

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?

Gives a concrete when-to-use trigger ('one sent to a mistyped address') and routes the agent to an alternative path ('correct the founder's email with save_application') when re-inviting is the goal. It does not explicitly contrast with redeem_invite or state when revocation is inappropriate, so it falls short of 5.

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