Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and openWorldHint, so the safety profile is covered. The description adds useful scope context: it clarifies that photo and review data are NOT returned here but live in sibling tools, which prevents over-expecting the payload. It does not add pagination or auth detail, but that is minor with output schema present.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.