Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the safety profile is covered. The description adds valuable behavioral context: the call is paid ($0.01 USDC), it handles partial failures with isolated results, and it is limited to public URLs. This goes beyond the schema and annotations, though it doesn't detail the exact response format for failures.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.