Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given no annotations, no output schema, and a simple but potentially underspecified operation, the description is incomplete. It doesn't explain what 'list' entails (e.g., format, keys, ordering) or handle edge cases. For a tool with zero structured metadata, more context on behavior and output would be needed for an agent to use it effectively.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.