Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does disclose meaningful traits: the challenge is private and read-only, causes no payment and no state transition, and the returned message must be signed locally. It omits other operationally relevant behavior such as challenge expiry, single-use semantics, and what the returned payload contains.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.