Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must fully disclose behavior. It only says 'import', which implies creation but gives no details on side effects, idempotency, or required authentication. The agent cannot infer if existing MCP collections are overwritten or if workspace deletion is possible.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.