Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
With no annotations, no output schema, and an empty input schema, an agent lacks essential information: how to specify the order, what data will be returned, and what authorization is needed. The statement 'Runs in your Kuudo deployment, not here' even suggests the operation is not available in the current context. This is not safely callable based on the description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.