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

Adds real behavioral context beyond annotations: the restore is non-destructive in the long run because it creates a new version that can itself be undone, which softens the destructiveHint. It doesn't state auth requirements or that the restore replaces current live content, but the key reversibility trait is disclosed.

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?

One front-loaded sentence that names the action, its undo purpose, the source of the parameter, and the reversibility. No wasted words.

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 mutation tool with full annotations and an output schema, the description covers purpose, parameter provenance, and the reversibility guarantee. Only minor gaps remain, such as whether the restored version becomes the live version immediately.

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 100%, so both site_id and version are already documented, including an example site id format. The description only adds that version numbers come from get_site with history: true, which is a minor semantic addition over the 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?

States a specific verb (restore) and resource (a saved version), and frames the operation as an undo, which is precise and distinguishable from siblings like update_site or create_site. It also names where the version numbers come from (get_site with history: true).

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?

Clearly contextualizes when to use it (to undo changes) and points to get_site with history: true as the source of version numbers. It doesn't name an explicit alternative for undoing the undo, but the mechanism is implied.

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