Creating tools for agents in LangChain

Introduction

Tools help agents do specific jobs easily. They let agents get information or perform tasks quickly.

When you want an agent to search the internet for answers.

When you need an agent to access a calculator or do math.

When an agent should check the weather or current news.

When you want to connect an agent to a database or API.

When you want to add custom commands for an agent to use.

Syntax

LangChain

from langchain.agents import Tool

tool = Tool(
    name="tool_name",
    func=your_function,
    description="What this tool does"
)

The name is how the agent calls the tool.

The func is the function the tool runs when used.

Examples

This tool adds numbers from a text input.

LangChain

def add_numbers(text: str) -> str:
    numbers = list(map(int, text.split()))
    return str(sum(numbers))

add_tool = Tool(
    name="Adder",
    func=add_numbers,
    description="Adds numbers given in text"
)

This tool returns the current time when called.

LangChain

def get_time(_input: str) -> str:
    from datetime import datetime
    return datetime.now().strftime('%H:%M')

time_tool = Tool(
    name="TimeChecker",
    func=get_time,
    description="Returns the current time"
)

Sample Program

This example creates a tool that greets someone by name. Then it uses the tool to greet "Alice".

LangChain

from langchain.agents import Tool

# Define a simple tool function

def greet(name: str) -> str:
    return f"Hello, {name}!"

# Create the tool
hello_tool = Tool(
    name="GreetTool",
    func=greet,
    description="Greets a person by name"
)

# Use the tool
result = hello_tool.func("Alice")
print(result)

Important Notes

Tools must have clear descriptions so agents know when to use them.

Functions used in tools should accept a single string argument and return a string.

Test your tool functions separately before adding them to agents.

Summary

Tools let agents perform specific tasks easily.

Create tools by defining a function and wrapping it with Tool.

Give tools clear names and descriptions for best results.

Practice

1. What is the main purpose of creating tools for agents in Langchain?

easy

A. To let agents perform specific tasks easily

B. To make the code run faster

C. To store data permanently

D. To create user interfaces

Solution

1. Step 1: Understand the role of tools in Langchain

   Tools are designed to help agents do tasks by providing specific functions.

2. Step 2: Identify the main benefit

   By using tools, agents can perform tasks more easily and effectively.

3. Final Answer:

   To let agents perform specific tasks easily -> Option A

4. Quick Check:

   Tools help agents do tasks = B [OK]

Hint: Tools help agents do tasks simply and clearly [OK]

Common Mistakes:

• Thinking tools speed up code execution
• Confusing tools with data storage
• Assuming tools create user interfaces

2. Which of the following is the correct way to create a tool in Langchain?

easy

A. tool = Tool(func=search_function)

B. tool = Tool('search', description='Searches data')

C. tool = Tool(name='search', description='Searches data')

D. tool = Tool(name='search', func=search_function, description='Searches data')

Solution

1. Step 1: Check required parameters for Tool

   The Tool constructor needs a name, a function (func), and a description.

2. Step 2: Match parameters with options

   Only tool = Tool(name='search', func=search_function, description='Searches data') provides all three: name, func, and description correctly.

3. Final Answer:

   tool = Tool(name='search', func=search_function, description='Searches data') -> Option D

4. Quick Check:

   Tool needs name, func, description = C [OK]

Hint: Tool needs name, function, and description to work [OK]

Common Mistakes:

• Omitting the function parameter
• Passing parameters in wrong order
• Leaving out the description

3. Given this code snippet, what will be the output when the agent uses the tool?

def greet(name: str) -> str:
    return f"Hello, {name}!"

from langchain.agents import Tool

greet_tool = Tool(name='greet', func=greet, description='Greets a person')

result = greet_tool.func('Alice')
print(result)

medium

A. "greet Alice"

B. "Hello, Alice!"

C. Error: Missing agent call

D. "Hello!"

Solution

1. Step 1: Understand the greet function behavior

   The greet function returns a string "Hello, {name}!" with the given name.

2. Step 2: Check how the tool is used

   The tool calls greet with 'Alice', so it returns "Hello, Alice!" which is printed.

3. Final Answer:

   "Hello, Alice!" -> Option B

4. Quick Check:

   greet('Alice') = "Hello, Alice!" [OK]

Hint: Tool calls function directly with given input [OK]

Common Mistakes:

• Thinking the tool prints 'greet Alice'
• Assuming an error without agent context
• Ignoring the name parameter in output

4. Identify the error in this tool creation code:

def add_numbers(a, b):
    return a + b

from langchain.agents import Tool

add_tool = Tool(name='add', func=add_numbers, description='Adds two numbers')

result = add_tool.func(5)
print(result)

medium

A. Missing one argument when calling add_tool.func

B. Tool name must be uppercase

C. Description is too short

D. Function add_numbers should not return a value

Solution

1. Step 1: Check function parameters

   add_numbers requires two arguments: a and b.

2. Step 2: Check function call

   add_tool.func is called with only one argument (5), missing the second argument.

3. Final Answer:

   Missing one argument when calling add_tool.func -> Option A

4. Quick Check:

   Function needs 2 args, call has 1 = D [OK]

Hint: Match function parameters with call arguments count [OK]

Common Mistakes:

• Ignoring argument count mismatch
• Thinking tool name case matters
• Assuming description length causes error

5. You want to create a tool that converts temperatures from Celsius to Fahrenheit for an agent. Which code correctly creates this tool with a clear description?

hard

A. def convert_temp(f):
return (f - 32) * 5/9

from langchain.agents import Tool

tool = Tool(name='temp_convert', func=convert_temp, description='Converts Fahrenheit to Celsius')

B. def c_to_f(c):
return c + 32

from langchain.agents import Tool

temp_tool = Tool(name='temp', func=c_to_f, description='Temperature conversion')

C. def c_to_f(c):
return (c * 9/5) + 32

from langchain.agents import Tool

temp_tool = Tool(name='temp_convert', func=c_to_f, description='Converts Celsius to Fahrenheit')

D. def c_to_f(c):
return (c * 9/5) + 32

tool = Tool(func=c_to_f, description='Convert temp')

Solution

1. Step 1: Verify function correctness

   The c_to_f(c) function returns (c * 9/5) + 32, which correctly converts Celsius to Fahrenheit using the standard formula.

2. Step 2: Check tool creation parameters

   Tool(name='temp_convert', func=c_to_f, description='Converts Celsius to Fahrenheit') uses name, func, and a clear description matching the task.

3. Final Answer:

   def c_to_f(c):\n return (c * 9/5) + 32\n\nfrom langchain.agents import Tool\n\ntemp_tool = Tool(name='temp_convert', func=c_to_f, description='Converts Celsius to Fahrenheit') -> Option C

4. Quick Check:

   Correct formula and clear tool setup = A [OK]

Hint: Use correct formula and full tool parameters [OK]

Common Mistakes:

• Using wrong temperature formula
• Omitting tool name or description
• Confusing Celsius to Fahrenheit with reverse