Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnly, idempotent, closed-world, non-destructive), so the bar is lower. The description adds genuinely new context by naming the source as a local ISTAT table (offline lookup, authoritative canonical formatting) rather than repeating the annotations; it is silent only on not-found behavior.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.