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

Adds substantial behavior beyond the annotations: 'Public and immediate', the confirmToken two-step flow with a summary on the first call, the resulting state change (fully reverted vs. still published with one part reverted), and the 422 failure mode. It is fully consistent with destructiveHint=true and idempotentHint=false.

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?

Dense but nearly waste-free, front-loaded with what gets restored. The main structural weakness is that the confirmToken requirement — critical to invoking the tool correctly — is buried in the final sentence rather than stated before or alongside the destructive note.

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?

With no output schema, the description names the return fields (status and revertedParts), covers error behavior, applicable states, and the confirmation workflow. An agent has everything needed to invoke this correctly.

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 75% and the schema only lists the enum values for `part`, but the description spells out exactly what each value restores (search = old title/H1/meta keeping new body; content = old body keeping current H1; all = both) and confirms the default. It also clarifies the confirmToken lifecycle beyond the schema's phrasing.

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+resource up front: restore the page to the pre-publish version. It also scopes applicability ('For published updates, and for flagged ones'), which implicitly separates it from the draft-side siblings like edit_update_draft, draft_update, and publish_draft.

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 clear usage context: published updates and flagged updates whose automatic revert could not be pushed. It also implies when the call is invalid (a part the update never changed answers 422). It never names an alternative sibling explicitly, so it stops short of the top band.

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