Tool Call Result

When a tool is delivered via app message, your client receives a conversation.tool_call event carrying a tool_call_id. To return a result, send a conversation.tool_result event back with the matching tool_call_id - that’s how Tavus pairs the result with the in-flight dispatch and applies the tool’s configured on_resolve. This applies to both LLM tools and Perception tools delivered via app message.

conversation.tool_result (sent by your client)

{
  "message_type": "conversation",
  "event_type": "conversation.tool_result",
  "conversation_id": "<conversation_id>",
  "properties": {
    "tool_call_id": "<id from the tool_call event>",
    "output": "It is 72 degrees and sunny in San Francisco.",
    "status": "success"
  }
}

Field	Type	Required	Description
`tool_call_id`	string	✅	Must match the `tool_call_id` from the original `conversation.tool_call` (or `conversation.perception_tool_call`) event.
`output`	string \| object	❌	The tool result. Strings are passed through; objects are JSON-serialized.
`status`	string	❌	`"success"` (default) or `"error"`. On `error`, the PAL acknowledges the failure instead of speaking the result.

If your client never sends a result, the dispatch eventually drops out of context. There’s no hard timeout on this path - the PAL just won’t have the data.

Perception tools are fire-and-forget by default, so the PAL does not pause for or react to a perception tool_result. Sending one is only meaningful when you’ve changed the tool’s on_resolve behavior.

Tool Call Event Started/Stopped Speaking Event

⌘I

Getting started

Build

Deploy

Debug

Guides

Resources

Tool Call Result