Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations indicate the tool is idempotent, not read-only, and not destructive. The description adds no behavioral context beyond what annotations already state—e.g., it doesn't explain what happens to the attention item after acknowledgment (e.g., removed, persisted) or if side effects occur.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.