What is the difference between tool_choice: "auto", "required", and "none" when binding tools to an LLM?

Question

Accepted Answer

The `tool_choice` parameter controls how the LLM behaves when given tool definitions. `"auto"` is the default, allowing the model to freely decide between responding with natural language or invoking a tool [citation:7]. `"required"` (often mapped from `"any"` in some SDKs) forces the model to make a tool call and cannot output text content alongside it, which can suppress chain-of-thought reasoning [citation:2]. `"none"` disables tool calling entirely, forcing a plain text response. You can also pass a specific tool name (e.g., `{"type": "function", "function": {"name": "get_weather"}}`) to force the use of a particular tool. ```python
from langchain_core.tools import tool
from langchain_openai import ChatOpenAI

@tool
def get_weather(location: str) -> str:
    """Get weather for a location."""
    return f"Weather in {location}: 72°F"

model = ChatOpenAI(model="gpt-4o")

# Auto: Model decides (default)
model_with_tools = model.bind_tools([get_weather], tool_choice="auto")
# Response could be text or tool call

# Required: Must call a tool (no text response)
model_with_tools = model.bind_tools([get_weather], tool_choice="required")
# Claude users: "required" can suppress chain-of-thought

# None: No tool calling
model_with_tools = model.bind_tools([get_weather], tool_choice="none")
# Forces plain text response only

# Specific tool: Force a particular tool
model_with_tools = model.bind_tools([get_weather], tool_choice={
    "type": "function",
    "function": {"name": "get_weather"}
})
``` A known limitation exists for Claude models: when `tool_choice="required"` (or `"any"`) is used with thinking enabled, the model cannot produce chain-of-thought text before the tool call, losing reasoning transparency [citation:2]. The fix, implemented in ChatAnthropic, downgrades forced `tool_choice` to `"auto"` when thinking is enabled, allowing CoT while still ensuring the required tool is called [citation:2].

What is the difference between tool_choice: "auto", "required", and "none" when binding tools to an LLM?

`tool_choice: "auto"` lets the model decide whether to call a tool; `"required"` (or `"any"`) forces at least one tool call and suppresses text responses; `"none"` disables tool calling entirely.

Scenario Questions

Follow-up Questions

What is the difference between tool_choice: "auto", "required", and "none" when binding tools to an LLM?

tool_choice: "auto" lets the model decide whether to call a tool; "required" (or "any") forces at least one tool call and suppresses text responses; "none" disables tool calling entirely.

Scenario Questions

Follow-up Questions

`tool_choice: "auto"` lets the model decide whether to call a tool; `"required"` (or `"any"`) forces at least one tool call and suppresses text responses; `"none"` disables tool calling entirely.