Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description is the only source of behavioral information. It implies a read-only introspection query and describes the field-level information the agent will receive. It doesn't disclose possible edge cases such as response shape, absence of data, authentication expectations, or side-effect-free guarantees, though the metadata nature of the tool makes those less critical.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.