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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description adds material context not in annotations: the deletion is irreversible, the subdomain stays permanently reserved, and a confirm mismatch refuses the call. The owner-only authorization rule and the 'ask the person, don't infer' instruction are exactly the behavioral disclosure this dimension rewards. It stops short of describing the returned result, though an output schema exists to cover that.

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?

The destructive outcome and irreversibility are front-loaded, and the alternative routing and permission rules follow in a logical order. It is dense but nearly every clause carries a distinct rule; the permission sentence is slightly convoluted but not wasteful.

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?

Covers the destructive scope, the irreversibility, the confirm-safety contract, the alternatives, and the authorization model, which is everything needed for a two-parameter irreversible mutation. Return values are handled by the output schema, so their absence from the description is not a gap.

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%, so the baseline is 3, and the description earns above that by giving operative meaning to `confirm`: it must repeat the site's own subdomain exactly, and the agent should obtain it from the person rather than synthesizing it from known context. That is procedural guidance the schema does not carry.

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 plus concrete scope: 'Takes a site down permanently — its files, its history and its subdomain.' This distinguishes it from pause_site and rollback_site, which are named later, so an agent can route without opening the schema.

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?

Names alternatives and the condition that selects them: 'To take a site off the air and keep it, use pause_site instead; resume_site brings it back.' It also states a hard precondition — only an account owner may delete — and tells the agent what to do when the caller is a team member.

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