Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false, openWorldHint=true, and idempotentHint=true, covering safety and idempotency. The description adds useful context about what data is returned (variant IDs, names, sizes, colors, preview images) and that variant IDs are needed for ordering, which isn't covered by annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.