Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description must disclose behavioral traits. It only describes parameters and return type but does not mention safety, idempotency, or potential side effects (e.g., if MIDI port is unavailable). This is insufficient for an AI agent to assess risks.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.