Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It does not state whether the operation is read-only, safe, or requires any permissions. The phrase 'Show terraform state' implies a read operation, but the agent cannot confirm safety or side effects.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.