Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With an output schema present, the description need not explain return values in detail. It covers scope, role, and side effects. The main gap is the absence of sibling-tool differentiation and the tension with the readOnlyHint annotation, but the description itself is otherwise complete for a single-parameter read-oriented tool.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.