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

Annotations already declare destructiveHint=true and idempotentHint=true, so the safety profile is covered. The description adds real value beyond that: precisely what gets destroyed (versions, storage files, members, access requests, view history), that the address stops working, and that recovery is impossible.

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?

Three short sentences, front-loaded with the destructive scope, then irreversibility, then the safer alternative. Every sentence earns its place with no filler.

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 two-parameter tool whose annotations already carry the safety flags, the description is complete: scope, consequences, irreversibility, and alternative are all covered. No output schema exists and none is needed for a delete confirmation.

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 50%; the 'confirm' parameter already carries 'Must be true' in the schema and siteId is a self-evident uuid. The description adds no parameter-level guidance whatsoever, so the schema is doing all the work here. Baseline 3 is appropriate.

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 wipe a site') and itemizes the exact scope: every version, storage files, people, access requests, and view history. An agent can distinguish it from neuron_sites_set_access or neuron_sites_update without opening any 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?

Explicitly names the alternative ('neuron_sites_set_access {paused:true}') and the condition that selects it ('to take it down temporarily instead'). It also gives the 'when not' signal via the irreversibility warning, leaving nothing to inference.

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