Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple tool with one parameter, an output-free description, and strong annotations (readOnly, idempotent, non-destructive), the description is complete. It tells the agent what the tool does, where the input comes from, and the nature of the returned data. No additional information is necessary for correct invocation.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.