Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the output schema exists and annotations cover safety, the description covers the essential use case, constraints (mutual exclusivity, expiration, token-free), and exceptions (unfinished images). It does not elaborate on the response format but that's covered by output schema.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.