Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint and idempotentHint, covering the safety profile. The description adds meaningful behavioral context: the response is delivered 'in focus', includes gray-shaded combination partners, associated ICD codes, case rates, and footnotes, and the top-level catalog behavior when no code is given. It enriches the annotation picture without contradicting it.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.