Hey guys I am fine tuning an OpenAI LLM. If the fine tuning .jsonl file only has system, user and assistant prompts, eg { "messages": [ { "role": "assistant", "content": "Let me check the current weather for you. Please hold on..." } Would the VAPI voice agent understand over time to call the tool when that is said based on the description we set on the tools in VAPI? Would that work even though I'm not using this data in the fine tuning process? (Btw, should I be using this during fine tuning?): { "role": "assistant", "content": "", "function": { "name": "get_weather", "parameters": { "location": "London" }, "description": "Retrieves the current weather for the specified location." } } ], "async": false, "server": { "url": "https://n8n.example.com/weather" } Would love some insight if you may