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

Beyond the annotations' destructive/idempotent hints, it discloses refusal semantics for accepted invites, NOT_FOUND for cross-org ids, the no-op-on-repeat behavior, and the permission model. These are exactly the failure modes an agent needs before firing a destructive call.

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 critical constraint (fires before use, undo for invite_member) is front-loaded and every clause carries information. Minor deduction for the embedded ticket reference '(RTSC-729)', which is noise for an agent, and for packing multiple constraints into one long sentence chain.

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-param destructive tool with no output schema, it covers the permission requirement, error cases, and idempotency, which is most of what a caller needs. It does not describe what a successful call returns, leaving the agent to infer the success shape.

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 `inviteId` is already documented as coming from list_invites, so the description's provenance note largely restates the schema. Baseline 3 applies because the schema does the heavy lifting here.

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 up front ('Kill an invite before anyone uses it') and frames it relationally as 'the undo for invite_member', which immediately separates it from the other invite/member siblings. It also names the adjacent tools it is not (suspend_member) and the tool that feeds it (list_invites).

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 an explicit when ('a mis-sent invite'), an explicit when-not ('an ALREADY-ACCEPTED invite is refused'), and the correct alternative in that case (suspend_member removes the person instead). The authorization precondition ('Owner or admin, through your human principal') is stated rather than left to discovery.

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