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

Goes well beyond the annotations: the annotations only say destructive/non-idempotent, while the description adds the 24-hour expiry and the write-conflict guard, plus the rationale (reverting would overwrite someone else's change). That directly explains the failure mode an agent will hit.

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?

Two short sentences, the core action front-loaded, followed by the two constraints that govern success. No filler.

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?

An output schema exists so return values need no explanation, and annotations already declare the destructive/non-idempotent profile. The description supplies exactly the missing pieces – expiry and the precondition check – leaving nothing essential unstated.

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 description coverage is 0% and the single parameter is only implied by the phrase 'applied proposal', so the description does convey that proposal_id must reference a previously applied proposal. It adds nothing about identifier format or how to obtain one, which is the main gap at 0% coverage.

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?

Specific verb (revert) plus a precise resource (an applied proposal) and the exact target state (values read just before it was applied). An agent can distinguish it from apply_change and the propose_* family 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?

Gives a concrete usage window (24h after apply) and an explicit refusal condition (refused if the objects no longer hold what that apply wrote). It stops short of naming an alternative when undo is refused (e.g., re-propose via propose_change), so it is clear but not fully routing.

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