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

Annotations already declare destructiveHint=true, readOnlyHint=false and idempotentHint=false, but the description adds genuinely new context: the account-token auth requirement, the refusal conditions, that it 'Does not charge', and that repeating the call restores the version it replaced (reinforcing the non-idempotent behavior). It stops short of return format or any rate/claim-state caveats.

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?

Front-loaded with the auth note and the core action, then the sequencing and constraints. The final sentence about the human Restore screen is the weakest link and slightly disrupts flow, but every sentence carries substantive information.

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 two-parameter mutation with no output schema and full annotation coverage, the description supplies auth, refusal, cost, and repeat-call behavior, which is close to complete. The claim-screen sentence is a bit tangential and the response content is never hinted at.

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 100%, so both parameters are already documented with examples. The description only restates the confirm=true effect, adding no syntax or format detail beyond the schema, which matches the baseline of 3 when the schema does the heavy lifting.

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 and resource ('Restores the previous version of a site') and clarifies the underlying mechanism (undoes the last Update or Edit files save). It does not explicitly name a sibling, but the rollback semantics are distinctive enough against delete_site, update_site_settings, and edit_site_file that the agent can pick it correctly.

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 trigger (recovering the prior version after an Update/Edit save) and an explicit exclusion ('Refused for a suspended or inactive site'). It also flags that confirm=true is required to actually apply it, though it names no alternative tool for adjacent recovery tasks.

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