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

Annotations already declare destructiveHint=true and non-idempotent, but the description adds the non-obvious semantic that undo is itself a new change rather than a state rollback, plus the conflict-detection refusal rule. It does not spell out permissions/ownership enforcement mechanics beyond 'this person's own', so it stops just short of full behavioral coverage.

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?

A single front-loaded sentence with the action first and exclusions after; nearly every clause carries information. The colon-joined tail ('then edit the records instead') is syntactically tangled and slightly slows parsing, keeping it from a 5.

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 2-parameter mutation with full annotation coverage and no output schema, the description covers mechanism, refusal cases, and alternatives adequately. It never states what the caller receives back (presumably the new change id), which is the one remaining gap an agent might want.

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%, so the baseline is 3; the description adds real value by telling the agent where a valid `change` id originates (history or a write's change), which the schema only formats as "chg_…". `trip` is left entirely to the schema, which already sources it from list_trips.

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 ('Reverse') plus the resource ('one of this person's own changes') and immediately clarifies the mechanism ('as a new change'). The parenthetical naming the accepted id sources (an id from history or a write's change) distinguishes it from the sibling `write` and `history` tools 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?

Explicitly enumerates the refusal conditions — touched state changed since, someone else's change, membership/owner/offer changes, replaced links — and names the fallback ('then edit the records instead'). An agent knows both when to call it and where to route when it will fail.

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