Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already provide readOnlyHint=true, idempotentHint=true, destructiveHint=false. The description adds 'Read-only', which aligns with annotations but does not disclose additional behavioral traits (e.g., pagination or ordering). No contradiction.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.