Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden, and for a zero-parameter information tool that burden is light: it never states that the call is read-only, parameter-free, or returns static reference text rather than data. 'Read this to the person first' does add a behavioral instruction about delivery, which is more than a bare content list, but the safety/idempotency profile an agent would want is still unstated.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.