Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lowered. The description usefully adds that results are restricted to restaurants where the dining credit works, but says nothing about result count, ordering, or the meaning of the limit cap in practice.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.