Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already mark the tool as read-only, idempotent, and non-destructive. The description adds value by explicitly listing the return contents (fields, geometry type, record count, capabilities), giving the agent concrete expectations about what it will receive. It does not mention any caveats like potential performance issues, but that is acceptable for a read-only schema operation.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.