Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description fully discloses behavior: it generates cryptographic bytes (DRBG-derived), outputs hex or base64, includes a signed provenance receipt, and imposes key-based rate limits and quotas. No side effects mentioned, but as a read-like operation this is acceptable.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.