Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple one-parameter tool, the description, schema, and annotations together provide sufficient context. The description could mention side effects (e.g., immediate termination, cannot be resumed), but the idempotent and destructive hints already cover risk behavior, making the tool adequately specified.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.