Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations exist, so the description carries full burden for behavioral disclosure. It only states the action without detailing what the tool does beyond listing—e.g., whether it returns paths or IDs, if it is recursive, or if it requires graph context. This leaves significant ambiguity for an AI agent.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.