Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, openWorldHint, and non-destructive behavior. The description adds beneficial context about the `passthrough` field behavior per source and the dynamic nature of live connectors, which goes beyond the annotations. 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.