This happens because returning a streamText() result from a tool’s execute function doesn’t automatically stream with tool identification, it just shows up as normal assistant output.

The easiest fix is to enable toolCallStreaming in your streamText config so the tool’s output is properly tagged and streamed. For most cases, that’s all you need. But you can also manually collect stream chunks or handle tool output tracking on the frontend if you want more control.

Hi Pauline thanks for the response,

The documentation says that tool streaming should be on by default for v5 but that’s not what we observe.

For now we’ve switched to using createUIMessageStream and passing the writer into the tool, and manually sending the tool chunks out but this feels like a workaround rather than intended usage, and adds complexity.

I think what they mean by tool streaming is that the input streaming part is currently implemented, meaning the tool input can be streamed in. However, there’s no implementation for output-available streaming, which I’d also need.

Here’s a related discussion: https://community.vercel.com/t/can-i-stream-structured-tools-ouput/12124

12  {[parts.map](https://parts.map)((part) => {3    switch (part.type) {4      case "text":5        return part.text;6      case "tool-queryTool": {7        switch (part.state) {8          case "input-streaming":9            // This part is streamed10            return {JSON.stringify(part.input, null, 2)};11          case "input-available":12            return {JSON.stringify(part.input, null, 2)};13          // This part is not streamed14          case "output-available":15            return {JSON.stringify(part.output, null, 2)};16          case "output-error":17            return 18Error: {part.errorText}19;20        }21      }22    }23  })}242526@Pauline Is support for output streaming on the roadmap?