Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The readOnlyHint annotation already covers the safety profile. The description adds meaningful behavioral details beyond the annotation: it returns only articles (not answers, thoughts, or videos) and supports pagination via page_token. This is useful context for an agent deciding whether this tool fits the task.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.