Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a destructive one-parameter operation, the description covers the key context: what is deleted, where, and that it cannot be undone. An output schema exists and the annotations cover the destructive nature, so the description does not need to explain return values or safety posture. Minor details like failure atomicity or required permissions are not mentioned, but that is a small gap.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.