Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and openWorldHint=true, so the safety profile is covered. The description adds only 'all' and 'in a course', which is minimal extra behavioral context beyond what annotations and the course_id parameter already imply. No additional traits like return format, pagination, or filtering behavior are disclosed, but none contradict the annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.