----------------------------- **While I generate an answer, here are some sources that might be helpful**: * [Tools Calling]() * [Server Events]() * [Function Calling]() * [Get Assistant]() -----------------------------

### Answer For your situation: 1. **Combining Responses into One Function**: Vapi's design allows for flexible configurations of tool calls, but each tool call is typically configured to handle a specific function call independently. You can, however, structure your server's logic to aggregate responses (for instance, car descriptions) and return them in a single response. This would mean adjusting your backend to compile the necessary data into one cohesive response before sending it back to Vapi. Unfortunately, the capability to handle parallel function calls directly within a single tool call isn't explicitly supported as per the current documentation [(1)]() . 2. **Handling Multiple Responses**: If sending multiple responses is essential, make sure that your server's response structure aligns with what Vapi expects. According to the Vapi documentation, the server should send back a response in a JSON format that includes a "results" array, where each result is associated with a "toolCallId". This setup helps the Vapi system to understand and process multiple results correctly . Here’s an example response format that your server might use to send multiple car details:

json
{
  "results": [
    {
      "toolCallId": "call_XYZ",
      "result": "Description of car A"
    },
    {
      "toolCallId": "call_XYZ",
      "result": "Description of car B"
    }
  ]
}

Ensure your system uses the

"toolCallId"

correctly to correlate requests and responses accurately, as mismatches in these identifiers can lead to the issues you're experiencing. If adjustments to these configurations do not resolve the issue, it may be beneficial to review the server and network logs to identify any potential discrepancies in request handling or data transmission .

Since the docs above are telling me that I should combine them all into one webhook response, I will try that as well. Maybe pass the full result only once in the first result and nothing in any other toolcalls functions that come through.

Watch this video

I tweaked the prompt to specify to only execute the function once for all of the selected vehicles and that looks to have solved the multiple Tool Calls issue. This explicit statement wasn't required for my previous booking assistant but seems since I'm stating two vehicles it is generating these as multiples. Still curious on whether this trigger is coming from Vapi side or the LLM itself.