<!-- mobian-agent-page publisher="dailydev" canonical="https://daily.dev/posts/structured-tools-ddxp4svpk" -->

---
title: Structured Tools | daily.dev
description: LangChain introduces Structured Tools, a new abstraction letting agent tools accept multiple inputs of arbitrary types instead of a single string, made...
canonical: https://daily.dev/posts/structured-tools-ddxp4svpk
twitter:card: summary_large_image
twitter:site: @dailydotdev
og:type: website
og:site_name: daily.dev
og:title: Structured Tools | daily.dev
og:description: LangChain introduces Structured Tools, a new abstraction letting agent tools accept multiple inputs of arbitrary types instead of a single string, made...
og:url: https://daily.dev/posts/structured-tools-ddxp4svpk
og:image: https://api.daily.dev/og/posts/DDXP4SvPK.png
og:image:alt: Structured Tools
og:image:width: 1200
og:image:height: 630
og:locale: en
---

> ## Documentation Index
> Fetch the complete documentation index at: https://daily.dev/llms.txt
> Use this file to discover all available pages before exploring further.

# Structured Tools

**[LangChain](https://daily.dev/sources/langchain)** · 7 min read · 0 upvotes · 0 comments

## Summary

LangChain introduces Structured Tools, a new abstraction letting agent tools accept multiple inputs of arbitrary types instead of a single string, made possible by more capable models like gpt-3.5-turbo and gpt-4. A new StructuredChatAgent works natively with these tools, and two new toolkits ship alongside it: a file management toolkit and a stateful PlayWright web browser toolkit. The post covers how to define structured tools via StructuredTool.from_function or by subclassing BaseTool, plus an FAQ on backward and forward compatibility with existing string-based tools and agents.

## Full article

daily.dev links to this article rather than hosting it. Read it at the original source: <https://www.langchain.com/blog/structured-tools>

## Questions this post answers

### How do I create a LangChain tool that accepts multiple arguments instead of just one string?

Use the StructuredTool.from_function(your_callable) constructor, which infers the args_schema from the function's signature, or subclass BaseTool directly with a Pydantic args_schema for more control, defining _run and async _arun methods for the tool's logic. This lets an agent pass multiple typed arguments, such as a path and query_params dict, instead of a single string.

_daily.dev surfaces practical LangChain patterns for developers building multi-input agent tools._

### Which LangChain agent types are not compatible with structured tools that take more than one argument?

Structured tools with more than one argument are not directly compatible without customization with zero-shot-react-description, react-docstore, self-ask-with-search, conversational-react-description, chat-zero-shot-react-description, and chat-conversational-react-description. A new StructuredChatAgent (AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION) was built specifically to work natively with these multi-argument tools.

_Developers picking the right LangChain agent type for their tools can track compatibility notes on daily.dev._

### Are old single-string LangChain Tool objects still compatible with new agents built for StructuredTool?

Yes, older string-based Tool objects are forwards compatible because Tool shares the same base class as StructuredTool, so they work out of the box with newer agent executors. Tools expecting JSON-serialized string inputs may need modifications to interoperate cleanly with newer output parsers, or can be updated to the new structured format for better support.

_Teams migrating agent tooling can follow compatibility changes like this one via daily.dev._

## Similar posts on daily.dev

- [New in Agent Builder: all new agent chat, file uploads \+ tool registry](https://daily.dev/posts/new-in-agent-builder-all-new-agent-chat-file-uploads-tool-registry-4idreqj8d) · LangChain · 3 upvotes · 0 comments
- [LangGraph Tutorial: Building Tools-First Agents](https://daily.dev/posts/langgraph-tutorial-building-tools-first-agents-tjc9ltpqu) · SitePoint · 1 upvotes · 0 comments
- [Building a Tool-Calling AI Agent with LangChain, LangGraph, Groq and LangSmith](https://daily.dev/posts/building-a-tool-calling-ai-agent-with-langchain-langgraph-groq-and-langsmith-ulgchhdc9) · Medium · 0 upvotes · 0 comments
- [Your Agent Isn't Dumb. Your Tools Are.](https://daily.dev/posts/your-agent-isn-t-dumb-your-tools-are--grledaace) · The T-Shaped Dev · 3 upvotes · 2 comments
- [The Roadmap to Mastering Tool Calling in AI Agents](https://daily.dev/posts/the-roadmap-to-mastering-tool-calling-in-ai-agents-qebo0jagl) · Machine Learning Mastery · 1 upvotes · 0 comments

---

Tags: [#python](https://daily.dev/tags/python), [#llm](https://daily.dev/tags/llm), [#ai-agents](https://daily.dev/tags/ai-agents), [#langchain](https://daily.dev/tags/langchain)

[View this post on daily.dev](https://daily.dev/posts/structured-tools-ddxp4svpk)

```json
{"@context":"https://schema.org","@graph":[{"@type":"Organization","@id":"https://daily.dev/#organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180},"sameAs":["https://twitter.com/dailydotdev","https://github.com/dailydotdev","https://www.linkedin.com/company/daily-dev-ltd"]},{"@type":"WebSite","@id":"https://daily.dev/#website","url":"https://daily.dev","name":"daily.dev","publisher":{"@id":"https://daily.dev/#organization"},"potentialAction":{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https://daily.dev/search?q={search_term_string}"},"query-input":"required name=search_term_string"}}]}
{"@context":"https://schema.org","@type":"TechArticle","headline":"Structured Tools","url":"https://daily.dev/posts/structured-tools-ddxp4svpk","mainEntityOfPage":{"@type":"WebPage","@id":"https://daily.dev/posts/structured-tools-ddxp4svpk"},"datePublished":"2026-08-25T18:28:37.393Z","dateModified":"2026-09-14T06:55:36.019Z","description":"LangChain introduces Structured Tools, a new abstraction letting agent tools accept multiple inputs of arbitrary types instead of a single string, made...","image":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f7f6485c6da6a24a860129f2562ee27a?_a=AQAEuop","thumbnailUrl":"https://media.daily.dev/image/upload/f_auto,q_auto/v1/posts/f7f6485c6da6a24a860129f2562ee27a?_a=AQAEuop","isAccessibleForFree":true,"articleSection":"LangChain","inLanguage":"en","publisher":{"@type":"Organization","name":"daily.dev","url":"https://daily.dev","logo":{"@type":"ImageObject","url":"https://daily.dev/apple-touch-icon.png","width":180,"height":180}},"author":{"@type":"Organization","name":"LangChain","logo":"https://media.daily.dev/image/upload/t_logo,f_auto/v1/logos/0f4f2629e0724a849823f8cd0d913e13","url":"https://daily.dev/sources/langchain"},"commentCount":0,"discussionUrl":"https://daily.dev/posts/structured-tools-ddxp4svpk","interactionStatistic":[{"@type":"InteractionCounter","interactionType":{"@type":"LikeAction"},"userInteractionCount":0},{"@type":"InteractionCounter","interactionType":{"@type":"CommentAction"},"userInteractionCount":0}],"keywords":"python,llm,ai-agents,langchain","timeRequired":"PT7M"}
{"@context":"https://schema.org","@type":"BreadcrumbList","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https://daily.dev"},{"@type":"ListItem","position":2,"name":"LangChain","item":"https://daily.dev/sources/langchain"},{"@type":"ListItem","position":3,"name":"Structured Tools"}]}
{"@context":"https://schema.org","@type":"FAQPage","@id":"https://daily.dev/posts/structured-tools-ddxp4svpk#faq","mainEntity":[{"@type":"Question","name":"How do I create a LangChain tool that accepts multiple arguments instead of just one string?","acceptedAnswer":{"@type":"Answer","text":"Use the StructuredTool.from_function(your_callable) constructor, which infers the args_schema from the function's signature, or subclass BaseTool directly with a Pydantic args_schema for more control, defining _run and async _arun methods for the tool's logic. This lets an agent pass multiple typed arguments, such as a path and query_params dict, instead of a single string. daily.dev surfaces practical LangChain patterns for developers building multi-input agent tools."}},{"@type":"Question","name":"Which LangChain agent types are not compatible with structured tools that take more than one argument?","acceptedAnswer":{"@type":"Answer","text":"Structured tools with more than one argument are not directly compatible without customization with zero-shot-react-description, react-docstore, self-ask-with-search, conversational-react-description, chat-zero-shot-react-description, and chat-conversational-react-description. A new StructuredChatAgent (AgentType.STRUCTURED_CHAT_ZERO_SHOT_REACT_DESCRIPTION) was built specifically to work natively with these multi-argument tools. Developers picking the right LangChain agent type for their tools can track compatibility notes on daily.dev."}},{"@type":"Question","name":"Are old single-string LangChain Tool objects still compatible with new agents built for StructuredTool?","acceptedAnswer":{"@type":"Answer","text":"Yes, older string-based Tool objects are forwards compatible because Tool shares the same base class as StructuredTool, so they work out of the box with newer agent executors. Tools expecting JSON-serialized string inputs may need modifications to interoperate cleanly with newer output parsers, or can be updated to the new structured format for better support. Teams migrating agent tooling can follow compatibility changes like this one via daily.dev."}}]}
```

