Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Beyond the readOnlyHint annotation, the description discloses meaningful behavior: concurrent fan-out, results grouped by store, selection from the scored `list-stores` set, and graceful skipping of slow/failing stores. This gives the agent a realistic picture of execution semantics.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.