Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering the safety profile. The description adds a useful scope detail ('public documents') and the tag-based relationship, which lets the agent know that results are limited to public docs and shared tags. It does not disclose output formatting, but an output schema exists.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.