Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare read-only, idempotent, closed-world, non-destructive behavior, so the description only needs to add operational context. It does so with the ordering rule ('Open programs come first, soonest deadline first'), which tells the agent how to interpret the first results. Pagination/sign-in limits are covered only by the schema, so not a full 5.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.