# Error for message's assistant tool calls' id object **URL:** \ **Category:** Bugs\ **Tags:** gpt-35-turbo, api, tools\ **Created:** [February 14, 2024, 5:03pm UTC](https://community.openai.com/t/error-for-messages-assistant-tool-calls-id-object/626732 "2024-02-14T17:03:03Z")\ **Posts on this page:** 1\ **Showing post:** 2
**Author:** ![\_j](https://sea2.discourse-cdn.com/openai1/user_avatar/community.openai.com/_j/32/766292_2.png) [@\_j](https://community.openai.com/u/_j)\ **Post date:** [February 14, 2024, 5:12pm UTC](https://community.openai.com/t/error-for-messages-assistant-tool-calls-id-object/626732/2 "2024-02-14T17:12:53Z")
I wrote out a much longer tutorial, showing the building of tools as schemas, progressing to the inclusion of tools in a request that gets tool\_call emitted to you, then through including the two messages that must be returned in order to continue. > [@Function Calling Help - Model Doesn't Seem To Accept Function Prompt?](https://community.openai.com/t/function-calling-help-model-doesnt-seem-to-accept-function-prompt/558935/11): > > I decided to make the mega-demo. Going beyond this I might as well just write a chatbot with classes for handling simulated functions and showing rewriting them to a real API… # imports and set up the OpenAI client object with a shorter timeout from openai import OpenAI import json client = OpenAI(timeout=30) # Here we'll make a tool specification, more flexible by adding one at a time toolspec=[] toolspec.extend([{ "type": "function", "function": { "name": "get\_we… --- _[View the full topic](https://community.openai.com/t/error-for-messages-assistant-tool-calls-id-object/626732)._