Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint, idempotentHint, openWorldHint, and destructiveHint=false, covering the safety profile. The description adds default behavior notes ('股票/资讯热榜默认不跑', '默认 digest'), but these largely restate defaults already documented in the input schema, so the added value beyond structured data is minimal.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.