Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the transparency burden. It discloses the re-screening behavior, the return of current alert state, and the cost ($0.003 USDC via x402). It does not explicitly state whether it modifies anything, but the verb 'check' implies a read-only operation, and the cost note is a useful behavioral trait.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.