Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover readOnly, idempotent, and non-destructive safety. The description adds meaningful traits: 'Free; does not consume API quota' (cost/rate-limit behavior) and 'Content is an original AI synthesis with no verbatim community quotes' (content provenance). These go beyond annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.