Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, and non-destructive behavior. The description adds valuable semantic context by clarifying that plans and queued handoffs are never included, which is not directly inferable from the annotations. This helps the agent understand exactly what the result set contains.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.