I added tool functions to my Agent and reminded them to call these functions in the prompt, but I’m not sure if they are being called successfully or if the results returned by the tool functions are correct.
When I call the tool functions externally from the LLM, I get a correct return value. However, during the LLM’s reasoning process, I often notice some hallucinated values, so I suspect there might be an issue with the tool functions.
The tool functions are initialized with a reference object, and their main task is to describe the data of this reference object for the LLM to use.
Looking forward to your reply, thank you!
Hi @komiya
Thanks for reaching out and for using Agno! I’ve looped in the right engineers to help with your question. We usually respond within 48 hours, but if this is urgent, just let us know, and we’ll do our best to prioritize it.
Appreciate your patience—we’ll get back to you soon!
Hey @komiya , to view the tool calls, we can use this parameter in the agent: show_tool_calls=True,
Could you also please share the agent configuration so that we can replicate the issue. 
1 Like