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

Annotations already flag destructive/not-idempotent, and the description still adds real value: exactly what gets destroyed (every unpublished change), the friction of confirmation, and the outcome flags restored=false / reset=false when there is nothing to undo. The closing clause 'neither touches the other' discloses a non-obvious interaction guarantee that annotations do not carry.

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 tight sentences, front-loaded with the core definition and then the two modes, each followed by its parenthetical edge case. No filler; every clause carries either an action, a guard, or an edge-case outcome.

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 what is destroyed, the confirm gate, the nothing-to-undo signals, and cross-mode independence. What is missing is smaller: nothing about site_id scope (whole site vs single page) is stated in text, though the 'what' schema covers that for last_publish.

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 already documents both 'what' and 'confirm', so the description is duplicating some of that. It still adds meaning beyond the schema: the result flags ('restored=false when there is nothing to undo', 'reset=false when the site was never published') let the caller interpret the response, which is absent from the input schema.

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?

'One-step undo' with the two enum modes spelled out ('last_publish' reverts the most recent publish; 'draft' discards unpublished changes) is a specific verb+resource statement that lets an agent tell the two behaviors apart. The only gap is that it never contrasts itself with the sibling 'unpublish', which also reverses a publish and could be confused with 'last_publish'.

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?

It gives concrete selection conditions for each mode ('reverts the most recent publish' vs 'discards every unpublished change so the draft matches the live site') and an explicit precondition ('needs confirm: true, so ask first'). It stops short of naming alternatives such as unpublish, so it is clear context without explicit routing.

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