Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given only 2 parameters, no output schema, and sparse annotations, the description is too thin. It does not cover prerequisite conditions (e.g., commands must have been set), what happens if no parameters are provided, or the meaning of 'scope' variations. This is inadequate for safe invocation of a destructive operation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.