Call iD: c6c46f3f-57ae-4341-955f-8be8eeb5abe9 We’re using Vapi’s query tool with (GPT-4o model for assistant) **Problem**: After a successful tool call (result is returned cleanly as a quoted string), the agent remains silent and does not say the result — unless the user repeats the question. What we tried: --> Model set to gpt-4o --> Tool returns string like "result": "\"Studios start at AED 460K...\"" --> Tool config includes: { "type": "query", "messages": [{ "type": "request-start", "blocking": true }] } --> Added instructions in the system prompt: * Always parse the result from query_tool_NEW as a quoted string. * After the tool result is received, speak it naturally and follow up with a question. * Also tested with request-complete, async false, and without any tool call blocking. --> Still Not Working: The agent hears the query, calls the tool correctly, receives the result — but says nothing after tool return. No fallback or recovery logic is triggered. Would appreciate guidance on whether this is: A tool response formatting issue? Something in how GPT-4o handles tool messages? A known issue in Vapi’s execution pipeline? Kindly Suggest a Verified Workaround https://cdn.discordapp.com/attachments/1397328265370402926/1397328265651290112/image.png?ex=688152db&is=6880015b&hm=64fb4695a1949540dde0e49f19ad130cf6c47a20770b496340fed08f2739c180&

Have been having this issue since forever🤦🏻

I solved it by resetting the messages to Default. @✞Penclone using the tool update CURL on terminal. curl -X PATCH https://api.vapi.ai/tool/YOUR_TOOL_ID \ -H "Authorization: Bearer YOUR AUTH KEY" \ -H "Content-Type: application/json" \ -d '{ "messages": [] }'

But I am using this with webhook response and the json format is different

webhook response....you mean you are using an external tool like n8n?

Ive tried it It doesn't

free vapi account?

Yes brother

Hey! I'm running into an issue with my agent - When I remove the startMessage and completeMessage from the query_tool, the agent sometimes cuts off mid-sentence or skips part of the reply as soon as the tool is called. But when I keep those messages in the tool config, the agent completes the tool call but then goes completely silent unless the user speaks again. Is there a reliable fix for this? It's honestly super frustrating

I'm having the same issue

You have a few options here: - Use Async: false - Use Async: true but use system role for complete message - Use Async: false with no messages at all Let us know which configuration works best for your use case!