Questions

21 of 24

1What is a Tool in LangChain and how does it differ from a plain function or API call?

2What is the difference between the tool() helper, DynamicTool, and StructuredTool class?

3How does an LLM decide which tool to call — what role does the tool description play?

4What is the role of Zod schema in tool definitions and how does it map to OpenAI's function calling spec?

5What is a ToolNode in LangGraph and how does it differ from calling a tool manually inside a graph node?

6How do you wrap a REST API call with auth headers inside a Tool in TypeScript?

7How do you handle async errors and retries inside a Tool without crashing the agent loop?

8How do you pass runtime context (userId, authToken, DB connection) into a Tool using RunnableConfig?

9How do you build a Toolkit (grouped set of related tools) using BaseToolkit?

10How do you validate and sanitize tool output before it is passed back to the LLM?

11How do you stream tool call results back to the client in real time?

12How do you implement tool-level authorization — allowing certain tools only for certain users?

13How do you build stateful tools that read/write to a database across multiple agent turns?

14How do you prevent tool abuse or infinite loops where an agent keeps calling the same tool repeatedly?

15How do you implement parallel tool calling — when the LLM decides to call multiple tools simultaneously?

16How do you create a human-in-the-loop tool that pauses the agent and waits for user approval before executing?

17How do you unit test and mock tools in isolation without invoking the LLM?

18How do you implement tool call caching to avoid redundant API calls for identical inputs?

19How do you design a multi-agent system where one agent's tool is actually another agent (agent-as-tool pattern)?

20How does LangGraph's ToolNode handle tool call errors and surface them back into the message state?

21What is the difference between tool_choice: "auto", "required", and "none" when binding tools to an LLM?

22How do you implement dynamic tool loading — where the set of available tools changes based on user role or session state?

23How do you trace and observe tool call latency in production using LangSmith?

24What are the token cost implications of registering too many tools and how do you mitigate it?

langchain

Context Engineering

Human in the loop

21 / 24

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.

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.

Tool Choice Examples

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].