Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and destructiveHint, so the tool is known to be safe and non-mutating. The description adds valuable behavior details: the inclusive count formula using absolute difference and the multi-unit return values. This goes beyond annotations and clarifies the calculation method.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.