restore_site

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

The description adds crucial behavior beyond the annotations: it is destructive to current config, requires confirmation, test-renders before enabling, rolls back automatically on failure, and does not reload nginx. These details complement the destructiveHint:true annotation and do not contradict it.

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 short sentences, each with a distinct role: purpose, destructive guard, failure mitigation, and the reload follow-up. Information is front-loaded and there is no filler.

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?

Given the destructiveHint annotation and the presence of an output schema, the description covers everything an agent needs: what is restored, the safety mechanism, the confirmation gate, and the necessary next-step reload. There are no hidden gaps.

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 parameters are already well-documented (including the confirm default/dry-run and archive_filename default). The description restates the confirm requirement but does not add new parameter-level information, so the baseline 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?

States a specific verb ('restore'), a precise resource ('domain's nginx config'), the source ('most recent archive created by delete_site'), and the outcome ('enable it'). This clearly positions the tool as the inverse of delete_site and distinguishes it from create_site and reload_nginx.

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?

The description states the mandatory confirm:true requirement, notes that confirm:false is a dry run, and explicitly instructs the agent to call reload_nginx afterward because this tool does not reload nginx. This is actionable usage guidance with a clear boundary.

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