Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already indicate read-only, idempotent, and non-destructive behavior. The description adds complementary behavioral context by detailing the return content ('per-visit and monthly ranges, labor, crew, schedule assumptions, and a visual report') and clarifying that it is non-binding and free, which goes beyond the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.