Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-branch, destructive, external-calling tool with no output schema, the description covers both actions, the confirmation gate, and the boundary against the sibling registration tools. It stops short of describing sync's return value or the irreversibility of discard, which would complete the picture for a destructive operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.