Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description is the sole safety signal. 'List' implies a non-destructive read operation and 'recent' implies a time-based ordering, but it does not disclose auth requirements, pagination, or whether the listing modifies read/unread state. This is adequate for a simple read-only tool but leaves behavioral gaps.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.