Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description goes well beyond that by disclosing the candidate pool, the per-claim metadata (facts, citations, base rate, confidence, school), and hard editorial filters — nothing common to most charts, nothing that flips with a 15-minute birth-time error, nothing on death/longevity/illness/fertility/separation. Those filtering rules are behavior an agent could not infer from structured fields.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.