Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations declare the safety profile (destructive, idempotent, open world), and the description adds genuinely new operational detail: SSRF guarding, size/count/time caps, atomic patch-mode application, and that platform-domain images are skipped. This is substantially more than the annotations provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.