Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations cover the safety profile (readOnly, idempotent, non-destructive, openWorld), but the description goes further: it discloses the $0.01 cost, the payment fallback behavior, the shape of each returned series (value, unit, effective/last-confirmed dates, source, confidence), and the risk of values being silently retired without an alert.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.