Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a two-parameter tool with an output schema, the description covers authentication, cost, parameter semantics, defaults, and enumeration. The only minor gap is the implied 'coin' dimension in the output, which is not explained as a filterable input, but the output schema likely covers the return structure.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.