エージェントにツールを与える
AIがWeb、ファイル、コードを使えるようにします。
「エージェントにツールを与える」はCoddyKit上の無料Vibe Codingレッスンです。 これはレッスン2/4です。 下記で完全なレッスンを無料で読むことができます。その後、ブラウザ内の組み込みコードエディタと24時間対応のAIチューターでハンズオン演習できます。 これはVibe Coding学習パスの一部であり、ウェブとCoddyKitアプリ全体で進捗が同期されます。 Vibe Codingコースには全4レッスンが含まれています。
このレッスンの一部はまだ翻訳されておらず、英語で表示されています。
Tools Turn a Chatbot Into a Doer
An agent is only as capable as the tools it can reach. On its own, an AI just predicts text. Give it tools, and it can search the web, read your files, run code, or call an API.
Think of tools as the agent's hands. The brain decides; the hands act. This lesson shows what those hands are and how you grant them.
What Counts as a Tool
A "tool" is any action the agent can take in the real world. Common ones:
- Web search / fetch — look something up online
- File read/write — open and edit your project
- Run command — start a server, run tests
- Call an API — hit a weather, payment, or data service
In Claude Code these come built in; in custom agents, you wire them up yourself.
Why Tools Matter
Without tools, an agent can only guess from what it already learned. It might say "the latest version is 3.2" when it's actually 5.0.
With a web search tool, it can go check. With a file tool, it sees your actual code instead of imagining it. Tools replace guessing with knowing — that's the whole point.
How a Tool Call Works
When an agent uses a tool, it doesn't run the tool itself — it requests it. The agent says "call getWeather for Paris," your system runs that function, and hands the answer back to the agent.
Here's that handoff as plain JavaScript so you can see the shape of a tool:
// A simple "tool" the agent can ask to use
function getWeather(city) {
const fake = { Paris: "18 C, sunny", Tokyo: "24 C, rain" };
return fake[city] || "unknown";
}
// Agent decides to call it; your code runs it; result goes back
const toolResult = getWeather("Paris");
console.log("Tool returned:", toolResult);Describing a Tool to the AI
For an agent to use a tool, you describe it in plain words: its name, what it does, and what inputs it needs. The AI reads that and decides when to call it.
You rarely write this by hand for beginner tools — Claude Code and v0 handle it — but knowing the shape helps you understand what the agent is choosing between.
A tool description the AI sees (plain language):
name: getWeather
description: Get the current weather for a city.
input: city (string) — the city name, e.g. "Paris"
Given that, the agent knows: "To answer a weather question,
I should call getWeather with the city."The Built-in Tools You'll Use Most
As a vibe coder, you'll lean on a handful of built-in tools your agent already has:
- Read file — so it understands your project
- Edit file — so it can build features
- Run command — so it can test and start things
- Web search — so it stays current
You mostly just allow these when asked. Knowing what each does helps you approve wisely.
Asking the Agent to Use a Tool
You don't have to name the tool — describe the outcome and the agent picks the right one. But you can nudge it when helpful.
Notice how this prompt hints at which tools to use without micromanaging:
Prompt that guides tool use (Claude Code):
"Search the web for the current version of React, then update
the version number in my package.json and README. Read both
files first so you don't break anything, and show me the diff
before saving."MCP: A Universal Tool Plug
You may hear about MCP (Model Context Protocol). It's a standard way to plug extra tools into an agent — like connecting it to your database, your design files, or a service like GitHub.
You don't need to build MCP servers as a beginner. Just know: it's the "USB port" that lets agents safely reach new tools beyond the built-in ones.
Connecting an API as a Tool
One of the most useful tools is a web API — a service your app calls for data (weather, currency, maps). An agent can both write the code that calls it and use it while building.
Here's a real fetch the agent might generate to call an API and use the result:
// Calling an API tool with fetch
async function getRate() {
const res = await fetch("https://api.frankfurter.app/latest?to=EUR");
const data = await res.json();
console.log("1 USD =", data.rates.EUR, "EUR");
}
getRate();More Tools Isn't Always Better
Every tool you give an agent is a power and a risk. A delete-file tool can clean up — or wipe your work. A shell tool can install packages — or run something harmful.
Good rule: grant the fewest tools needed for the task. Start narrow, add more only when the job clearly needs it. You'll go deeper on this in the safety lesson.
You Equip, the Agent Acts
Putting it together: you decide which tools the agent can reach, describe what each does, and approve their use. The agent then chooses the right tool at the right moment to reach your goal.
An agent without tools is just a chatbot. An agent with the right tools is a builder. Equip it thoughtfully and it becomes genuinely useful.
Quick Check
Let's confirm what a tool really is to an agent.
Recap: Hands for the Agent
You learned how agents reach the real world:
- Tools are actions: web search, file read/write, run command, call an API.
- The agent requests a tool; your system runs it and returns the result.
- Each tool is described by name, purpose, inputs.
- MCP is the standard plug for adding extra tools.
- Grant the fewest tools needed — power equals risk.
Next: chaining tools and steps into a multi-step automation.
よくある質問
「エージェントにツールを与える」レッスンは無料ですか?
はい。「エージェントにツールを与える」の完全なテキストはこのウェブで無料で読めます。インタラクティブに演習し(組み込みコードエディタと24時間対応のAIチューター)、Vibe Codingコースの残りをアンロックするには、CoddyKit PROにアップグレードしてください。 Vibe Codingコースには全4レッスンが含まれています。
「エージェントにツールを与える」で何を学びますか?
AIがWeb、ファイル、コードを使えるようにします。 ブラウザで直接実行するハンズオンコードでVibe Codingを演習し、24時間対応のAIチューターがレッスンを進める中での質問に答えます。
Vibe Codingを始めるのに経験は必要ですか?
事前経験は必要ありません。CoddyKitのVibe Codingは初級者から上級者向けに構成されているため、ここから始めるか最初から始めて、自分のペースで進むことができます。 これはレッスン2/4です。
「エージェントにツールを与える」レッスンにはどのくらい時間がかかりますか?
ほとんどのCoddyKitレッスンは約5~10分かかります。各レッスンはコンパクトでインタラクティブなので、着実に進歩し、ウェブとアプリ全体で正確に前回の場所から再開できます。
このVibe Codingレッスンでコードを書いて実行できますか?
はい。すべてのVibe Codingレッスンに組み込みコードエディタが含まれているため、ブラウザでリアルコードを書いて実行し、即座のAIフィードバックを取得できます。ローカル設定は不要です。
このコースのすべてのレッスン
- アシスタントからエージェントへ
- エージェントにツールを与える
- 複数ステップのタスク自動化
- エージェントを安全に保つ