Just based on my experience using langchain/langgraph as AI orchestrator ... from my understanding, the LLM doesn't actually invoke the tool, it just reply with the tool function and arguments. You'll need the AI orchestrator to actually make the call

Ref: https://python.langchain.com/docs/how_to/tool_calling/

Remember, while the name "tool calling" implies that the model is directly performing some action, this is actually not the case! The model only generates the arguments to a tool, and actually running the tool (or not) is up to the user.