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

Annotations already declare destructiveHint=true and idempotentHint=false, and the description adds real substance beyond them: exactly what is destroyed (audits and readiness history), that the operation is irreversible, and a refusal rule tied to CMS connectivity. That CMS precondition is behavior an agent cannot infer from the schema or annotations.

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 with the destructive effect and the irreversibility warning. The CMS clause is awkwardly phrased and its parenthetical is hard to parse, which costs a point but not usability.

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 an output schema exists, the description needn't explain returns. It covers cascade scope, irreversibility, the blocking precondition, and pointers to related tools — enough for an agent to decide and call correctly.

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 the single siteId parameter is documented in the schema as 'Site id from list_sites.' The description doesn't add syntax, format, or sourcing detail beyond that, so the schema carries the load and baseline 3 applies.

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 ('permanently removes') and resource ('a website'), plus the exact cascade scope ('its audits and readiness history'). This clearly separates it from sibling deletion tools such as delete_post, delete_assets, and delete_source, which operate on other resources.

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?

Provides an explicit precondition/exclusion: a site that a CMS publishes to is refused until the CMS is disconnected or moved. It also names the relevant related tools (get_website_cms, list_sites, save_site). What's missing is an explicit statement of the alternative action for the blocked case, but the practical routing signal is unusually strong.

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