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

Annotations already declare destructiveHint, idempotentHint, and readOnlyHint=false, so the safety profile is covered. The description still earns credit for adding genuinely new behavior: deletion is asynchronous with a transient 'deleting' status, and the site address remains reserved rather than released. It does not say whether data is recoverable or what the call returns, leaving the most consequential question open. (Scored 3 rather than 4 because the redundant 'until then ... until then' phrasing muddies the one behavioral claim it makes.)

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?

Short and front-loaded, but the duplicated clause 'and until then its status reads deleting until then' is a clear editing error that wastes the most important sentence. The permission requirement trails at the end where it would be better placed before the effects.

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 single-parameter destructive tool with no output schema, it covers the timing of the effect, the intermediate status, the address reservation, and the required capability. The main gap is recoverability — whether anything can be undone or restored — which matters for a destructive operation.

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% and siteId already points at 'Site id from list_sites', so the schema carries parameter meaning. The description adds nothing about the identifier, which is acceptable given full schema coverage — 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?

States a specific verb (delete) and a scoped resource ('SHIP-hosted site'), which separates it from the sandbox/template deletion siblings that share the delete_ prefix. It stops short of naming a specific alternative, but the resource qualifier does the disambiguation work.

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?

Usage is only implied by the verb; there is no explicit statement of when to delete versus roll back (rollback_site), update (update_site), or remove a domain (remove_site_domain). The 'address stays held' note hints that this is not a clean-slate teardown, but no conditions or exclusions are spelled out.

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