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

Annotations already flag destructiveHint=true and idempotentHint=true, but the description adds substantial non-structured context: irreversibility, that files and versions are destroyed, the account-token prerequisite, the three refusal preconditions, and that no charge is incurred. This is exactly the behavioral detail annotations cannot express.

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?

Five short sentences, front-loaded with the irreversible destructive action and the auth prerequisite, then the refusal conditions, then the confirm mechanics. No filler or redundancy.

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 destructive tool with no output schema, the description covers preconditions, irreversibility, side effects (files/versions, no charge), and the confirm gate. Nothing an agent needs before invoking it is missing.

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' and 'confirm' are already fully documented in the schema. The description's 'confirm=true applies it' merely restates the schema's declaration of the same semantics, adding no new syntax, format, or default information.

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 (Deletes) and resource (a site) and immediately scopes what is removed: 'including its files and versions.' This is clearly distinguishable from siblings such as rollback_site, deploy_site, or turn_off_email, none of which remove a 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?

Gives explicit refusal conditions (domain registered here, email still on, suspended site) and the confirm=true requirement, so the agent knows when the call succeeds versus fails. It does not, however, name an alternative tool (e.g. turn_off_email or transfer_domain_out) for the blocked cases, leaving that routing to inference.

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