Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description adds significant behavioral context beyond annotations: it clarifies the index is 'fixed-basket same-card index (never vibes)', states it's 'not investment advice', and lists specific output components (phase read, peak/drawdown, sale counts, calendar). Annotations only declare readOnlyHint and non-destructive, so description bears full burden and does so well.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.