Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a tool with complex eligibility rules and side effects, everything needed to call it correctly is present: type of listing it applies to, seller prerequisites, exclusion cases, error behavior, pending-only semantics, the follow-up tool, and authentication. An output schema exists, so explaining return values is unnecessary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.