Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, so the description adds no behavioral insight. Without any output schema or further details, the agent cannot infer what data is returned or if there are any side effects beyond being read-only. The description fails to disclose the scope or granularity of analytics (e.g., workspace-level vs per-site).
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.