Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations provide strong behavioral hints (readOnlyHint: true, destructiveHint: false, idempotentHint: true, openWorldHint: true), so the description's burden is lower. However, it adds no context beyond what annotations already cover—no information about authentication requirements, rate limits, or what specific user data is returned. The description doesn't contradict annotations, but it adds no value.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.