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

Annotations already declare destructiveHint=true and idempotentHint=false, yet the description still adds substantive context: the invite can no longer be joined, only the minting seat or another seat with invite rights may revoke, and the calling seat is excluded. That permission/effect detail is exactly what 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?

Six short, front-loaded sentences with no filler: effect first, eligibility second, permissions third, endpoint and safety last. Every sentence carries an operational fact.

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, non-idempotent mutation with no output schema, the description covers effect, eligibility, authorization and endpoint. It stops short of describing error or failure behavior, which would matter for a non-idempotent operation.

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 schema already documents invite_url as an alternative to join_token and join_token as URL-or-raw-token. The description restates the same URL-or-token flexibility without adding format or precedence rules, so it matches the baseline rather than exceeding it.

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 one unused invite by join_token') and constrains scope to unused invites. The agent can distinguish it from create_invite/get_invite, and the 'unused' qualifier separates it from seat revocation.

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?

'Revoke one unused invite' plus 'Used invites stay spent' tells the agent which invites qualify, and 'Does not revoke the calling seat' hints that seat revocation is a different operation (revoke_seat). It never names revoke_seat explicitly as the alternative, so routing is inferred rather than stated.

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