Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, openWorldHint=false, and idempotentHint=true. The description adds useful behavior beyond that: it is data-only, never renders a search card, and expects the agent to provide prose with source links, which clarifies output handling.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.