evident-indigo
evident-indigo4d ago

Agent does not pick up on the result supplied by tool calling?

It clearly shows that tool calling was successful and provided a result. But the AI keeps gaslighting and telling me that the results haven't come in yet. What could be causing this? Call ID: 019ae3cb-7d41-7cc2-8b84-790b029312bb
No description
9 Replies
Vapi Support Bot
Thank you for sharing the details of your experience. Based on the information provided, it appears that the tool calling was successful and returned a result, but the AI did not acknowledge or use that result as expected. Unfortunately, I do not have access to specific technical logs or internal diagnostics that would allow me to determine the exact cause of this behavior. If you have any additional details or patterns you've noticed, feel free to share them, and I'll do my best to help with the information available.
⤵️ Mention @Vapi Support Bot for follow-ups 🐥
evident-indigo
evident-indigoOP4d ago
Ok so switching to a different model seems to solve this issue immediately. Does GPT-Realtime Cluster not support tool calls?
genetic-orange
genetic-orange4d ago
+1 to this issue. I'm having the same problem
Vapi
Vapi2d ago
Your assistant prompt needs explicit instructions on how to handle scheduling appointments. You are correct that it has the data, but it just doesn't know what to do with it. Add instructions in the prompt like this example:
Once the `check_calendar_availability` tool has returned some results, ask what time the user would like to schedule. if they don't have a specific time in mind, suggest three of the times from the result. once the user has picked a time, use the `create_calendar_booking` and create a calendar event for that time.
Once the `check_calendar_availability` tool has returned some results, ask what time the user would like to schedule. if they don't have a specific time in mind, suggest three of the times from the result. once the user has picked a time, use the `create_calendar_booking` and create a calendar event for that time.
evident-indigo
evident-indigoOP2d ago
It's still not reliable after adding those specific instructions. Here's a call with GPT Realtime Cluster: 019aed68-e8ae-7ff9-9850-52ebff81b86f I swapped model to GPT 5.1 without changing anything else and these were the results: 019aed6b-2255-7ccd-9bdb-104c2c92c94a
evident-indigo
evident-indigoOP2d ago
GPT Realtime Cluster
No description
evident-indigo
evident-indigoOP2d ago
GPT 5.1
No description
evident-indigo
evident-indigoOP2d ago
As you can see not only does it handle the function call properly, it also gives a reply without me having to ask for it
evident-indigo
evident-indigoOP2d ago
I found another support thread about this specific issue with gpt-4o-realtime-preview 8 months ago: https://vapi.ai/community/m/1364937699265613824
Does OpenAI realtime support tool calling? - VAPI
I can't get it to call any of my tools, including the built in ones? The docs only state that the knowledge base doesn't work—so I expected tools to work.

Did you find this page helpful?