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

Annotations only say destructiveHint=false; the description explains WHY — the restore is appended as a new version on top of history, nothing is deleted, and the restore itself can be undone. That is exactly the non-obvious behavioral fact an agent needs before mutating a site, and it is consistent with idempotentHint=false (repeating creates another version).

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?

Four sentences, front-loaded with the non-destructive guarantee, which is the highest-value fact. The final courtesy instruction is arguably operational guidance rather than tool semantics, but it is short and earns its place.

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?

Covers purpose, safety model, version sourcing, scoping options, and a usage protocol for a 5-parameter mutation with annotations present. The remaining gap is outcome: with no output schema, the description does not say what is returned (e.g. the new version number) or how to confirm the restore.

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 the schema already documents all five parameters, and the description's mention of file_slug and variation_index largely restates their schema text. It adds no format or interaction detail (e.g. whether file_slug and variation_index can be combined) and never mentions user_goal. Baseline 3.

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+resource ("Restore a site to a previous version") with an explicit source for the version (list_versions), which names the sibling that produces the required input. An agent can distinguish this from list_versions or clone_site without opening either 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 clear prerequisite (version number comes from list_versions) and a pre-call protocol ("Tell the user which version you are rolling back to and why before calling this"). It also states the optional narrowing cases. It stops short of stating when NOT to use it (e.g. versus clone_site or switch_variation), so it is strong context rather than full routing.

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