Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint/ idempotentHint/ openWorldHint and non-destructive, covering the safety profile. The description adds genuine context: real-time event-stream semantics, second-level timestamps, and the required markdown-link format for stocks — behavior beyond the annotations, though it doesn't mention rate limits or staleness of the stream.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.