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

Annotations declare destructiveHint=true, but the description goes well beyond them by disclosing the two-phase protocol: the first call returns only a summary and confirmToken, and nothing is revoked until the token is passed back. That is exactly the behavioral detail an agent needs to avoid a half-finished 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 short sentences, each doing distinct work: purpose, exclusion, and protocol. The destructive two-step warning is stated up front rather than buried, and there is no restatement of the name or title.

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?

With no output schema, the description still tells the agent what the first call returns (summary + confirmToken) and how to complete the operation. Combined with annotations covering the safety profile, nothing essential for correct invocation is missing.

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% and confirmToken is already documented in the schema, but the description ties it to the actual workflow ('call again with confirmToken to proceed'), reinforcing the required sequencing. It says little about inviteId, though 'pending invitation' implicitly scopes it to an invitation identifier.

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 ('Withdraws a pending invitation') plus the concrete effect ('its link stops working'), and immediately bounds the scope with 'It does not remove a teammate who already accepted.' That negative clause separates it from invite_teammate and any teammate-removal tool without the agent having to open a 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?

Clearly establishes the condition for use — the invitation must still be pending — and rules out the adjacent case of an already-accepted teammate. It does not name a sibling alternative (e.g. resend_invite for the inverse intent), so it stops short of explicit routing.

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