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

The description states that the rollback 'records a new version' each time it is called, indicating a side effect that changes the site's version history. This directly contradicts the annotation idempotentHint=true, which claims the tool has no side effects when called multiple times with the same parameters. Therefore, the description contradicts the annotations, requiring a score of 1 and an annotation contradiction flag.

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 description is a single, well-organized paragraph that front-loads the usage trigger, then explains the behavioral nuance (content only, address unchanged) and points to list_versions. Every sentence adds value, and there is no unnecessary verbosity.

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?

The description covers the key behavioral aspects: it restores content, records a new version, leaves slug/folder/visibility unchanged, and notes the share URL behavior. It also provides the version_id source. It does not explain the return value or potential errors, but for a mutation tool without an output schema, this is acceptable. However, the contradiction with idempotentHint leaves a gap in clarity about idempotency, so it is not fully complete.

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?

The schema already provides full descriptions for all three parameters, including the note that version_id comes from list_versions. The description does not add new meaning beyond what the schema states; it merely repeats the reference to list_versions. Since schema coverage is 100%, a baseline of 3 is appropriate.

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?

The description clearly states the tool's purpose: undo the last update or go back to a previous version by restoring prior content. It uses a specific verb (rollback) and resource (site version), and the behavior of recording a new version distinguishes it from other site-modifying tools like update_site or delete_site.

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 states when to use: 'when the user wants to undo the last update or go back to the previous version.' It also directs the agent to list_versions to obtain the version_id, providing a clear path to the prerequisite action. This differentiates it from alternatives and gives actionable context.

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