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

Annotations already declare destructiveHint=true and idempotentHint=false, so the description's job is scope. It does that well: 'permanently' plus the cascade to all files and the address tells the agent the blast radius exceeds a single resource. It stops short of noting irreversibility guarantees or whether files are recoverable.

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?

One sentence, front-loaded with 'Permanently removes' and no filler. Every clause (permanence, cascade to files, address) carries 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 destructive, non-idempotent mutation the description nails consequences but omits prerequisites — that an editKey credential is required and what happens on a wrong/expired key. With no output schema and 0% parameter documentation, those gaps matter.

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 0% for two required parameters, yet the description mentions neither websiteId nor the 64-hex editKey, and gives no hint that editKey is an authorization credential separate from the identifier. The agent gets no meaning beyond the raw patterns.

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 ('Permanently removes a website') and adds scope detail — every file and its address go with it — which separates it from delete_website_file. It also ties the target to start_website, so an agent knows this is the counterpart of site creation.

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?

Mentions 'started with start_website', which implies the lifecycle context for use, but never states when to prefer this over delete_website_file or that no confirmation/undo path exists. Usage is inferable rather than stated.

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