Building a Minimal Spring AI Tool Chain for Multi-Tool Calls

Scenario

Spring AI can call external tools from a large language model (LLM) and automatically compose their execution order, enabling agents to complete multi‑step tasks such as "query Beijing weather and answer in English".

Core Concepts

Tool Calling : The LLM generates a function‑call request (function name and parameters); Spring AI intercepts the request, invokes the corresponding Java method, and returns the result to the model.

@Tool annotation : Placed on a method, Spring AI parses the method signature and JavaDoc to produce a JSON Schema that the model can understand.

Multiple Tool Registration : Use defaultTools(...) to register several tools at once; the model decides the order and combination of calls.

Chain Calling : Within a single response the model can invoke multiple tools sequentially, feeding the output of one tool as the input to the next, forming a chain.

Implementation

pom.xml

<parent>
    <groupId>org.springframework.boot</groupId>
    <artifactId>spring-boot-starter-parent</artifactId>
    <version>3.3.3</version> <!-- downgrade to stable version -->
</parent>
<groupId>com.example</groupId>
<artifactId>spring-ai-ollama-tool-chain</artifactId>
<version>1.0</version>
<properties>
    <java.version>17</java.version>
    <spring-ai.version>1.1.2</spring-ai.version>
</properties>
<dependencies>
    <dependency>
        <groupId>org.springframework.boot</groupId>
        <artifactId>spring-boot-starter-web</artifactId>
    </dependency>
    <!-- Spring AI Ollama core -->
    <dependency>
        <groupId>org.springframework.ai</groupId>
        <artifactId>spring-ai-starter-model-ollama</artifactId>
        <version>${spring-ai.version}</version>
    </dependency>
</dependencies>

application.yml

server:
  port: 886
spring:
  ai:
    ollama:
      base-url: http://localhost:11434
      chat:
        model: qwen2.5:7b-instruct
        options:
          temperature: 0.7
          num-ctx: 4096 # context window size
logging:
  level:
    org.springframework.ai.chat.client: DEBUG # view tool‑call details

Weather Tool

package com.badao.ai.tools;
import org.springframework.ai.tool.annotation.Tool;
import org.springframework.ai.tool.annotation.ToolParam;
import org.springframework.stereotype.Component;

@Component
public class WeatherTool {
    @Tool(name = "get_weather", description = "查询指定城市的实时天气")
    public String getWeather(@ToolParam(description = "城市名称") String city) {
        System.out.println("调用了天气工具");
        // Simulated weather data
        return String.format("%s当前天气：晴，温度22℃，湿度45%%。", city);
    }
}

Translate Tool

package com.badao.ai.tools;
import org.springframework.ai.tool.annotation.Tool;
import org.springframework.ai.tool.annotation.ToolParam;
import org.springframework.stereotype.Component;

@Component
public class TranslateTool {
    @Tool(name = "translate_to_english", description = "将中文文本翻译成英文")
    public String translate(@ToolParam(description = "待翻译的中文文本") String text) {
        System.out.println("调用了翻译工具");
        // Simulated translation; real implementation could call a translation API
        return "Translated: " + text + " (This is the English version.)";
    }
}

Tool Registration Configuration

package com.badao.ai.config;
import com.badao.ai.tools.WeatherTool;
import com.badao.ai.tools.TranslateTool;
import org.springframework.ai.chat.client.ChatClient;
import org.springframework.ai.chat.model.ChatModel;
import org.springframework.context.annotation.Bean;
import org.springframework.context.annotation.Configuration;

@Configuration
public class ToolConfig {
    @Bean
    public ChatClient chatClient(ChatModel chatModel, WeatherTool weatherTool, TranslateTool translateTool) {
        return ChatClient.builder(chatModel)
            .defaultTools(weatherTool, translateTool) // register weather and translation tools
            .build();
    }
}

Agent Service Layer

package com.badao.ai.service;
import org.springframework.ai.chat.client.ChatClient;
import org.springframework.stereotype.Service;

@Service
public class AgentService {
    private final ChatClient chatClient;
    public AgentService(ChatClient chatClient) {
        this.chatClient = chatClient;
    }
    public String ask(String question) {
        return chatClient.prompt()
            .user(question + "（请先用天气工具，再用翻译工具）")
            .call()
            .content();
    }
}

Controller

package com.badao.ai.controller;
import com.badao.ai.service.AgentService;
import org.springframework.web.bind.annotation.*;

@RestController
@RequestMapping("/api")
public class AgentController {
    private final AgentService agentService;
    public AgentController(AgentService agentService) {
        this.agentService = agentService;
    }
    @PostMapping("/agent")
    public String ask(@RequestBody String question) {
        return agentService.ask(question);
    }
}

Testing

Test a single tool call and a chained tool call using the provided REST endpoint. The screenshots below show the console output for each scenario.