Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations present the description carries the full burden, and it does disclose one genuinely behavioral fact: login is required. The read-only, non-destructive nature is strongly implied by 'available' and returns are covered by the output schema, but nothing is said about whose addresses are returned or whether an unauthenticated call errors or returns empty.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.