Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description indicates it clears an in-memory cache, which is non-destructive but does not disclose side effects or scope. Since no annotations exist, the description carries the burden, but it omits details like idempotency, impact on other cached data, or performance implications.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.