Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a zero-parameter, no-output-schema tool, the description is reasonably complete on purpose. However, it does not describe the return format, frequency expectations for polling, or whether this is safe to call repeatedly. Sibling tools (get_obs_health, get_debug_config) offer overlapping 'get state' functions, and the description alone doesn't clarify where the boundaries are.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.