Langchain4j Tool Function Calling Patterns

This one teaches you how to wire up external function calls in LangChain4j agents using the @Tool annotation system. You annotate methods with @Tool and @P, register them with AiServices.builder().tools(), and the LLM can invoke them during conversations. The skill covers error handlers for when the model hallucinates tool names or passes bad arguments, concurrent execution for independent tools, and timeout configs for external API calls. It's practical if you're building agents that need to query databases, hit APIs, or perform calculations beyond what the LLM can do natively. The examples show calculator tools, email senders with immediate return behavior, and dynamic tool providers that change based on user context.

skills.sh installs: 3.9K
GitHub stars: 369
last updated: Aug 21, 2026

View on GitHub

Install

$ npx -y skills add giuseppe-trisciuoglio/developer-kit --skill langchain4j-tool-function-calling-patterns --agent claude-code

Installs into .claude/skills of the current project.

Files

LangChain4j Tool & Function Calling Patterns

Provides patterns for annotating methods as tools, configuring tool executors, registering tools with AI services, validating parameters, and handling tool execution errors in LangChain4j applications.

Overview

LangChain4j uses the @Tool annotation to expose Java methods as callable functions for AI agents. The AiServices builder registers tools with a chat model, enabling LLMs to perform actions beyond text generation: database queries, API calls, calculations, and business system integrations. Parameters use @P for descriptions that guide the LLM.