Agentic AI Notebook
Phase 12

Built-in Tools

~2 min read

Concept & How It Works

  • Key points are in the visual diagram above.

Why Does It Exist?

Coding agents need a small, boring tool set more than eighty vague plugins.

Real-World Analogy

A kitchen: knife, board, stove. You add a thermometer. You do not add a chainsaw by default.
Loading diagram...

Visual Workflows

What is Built-in Tools?

Loading diagram...

Example

Scenario

A kitchen: knife, board, stove. You add a thermometer. You do not add a chainsaw by default.

Solution

In Claude Agent SDK, apply Built-in Tools to this scenario: A kitchen: knife, board, stove. Identify the inputs, run the technique, validate the output, and note one thing you would monitor in production.

Practice Task

Do this before moving to the next module — reading alone is not enough.

Open the Code Walkthrough below and run it locally. Change one parameter related to Built-in Tools (e.g. model, temperature, top_k, or tool name), observe the difference in output, and write 2–3 sentences explaining what changed.

Code Walkthrough

Highlighted lines show where Built-in Tools happens in the code.

Built-in Tools
1options: { allowedTools: ["Read", "Grep"], disallowedTools: ["Bash"] }  # key line for Built-in Tools

Commands to Remember

Commands to Remember

  • npm install @anthropic-ai/claude-agent-sdk # Claude Agent SDK
  • pip install claude-agent-sdk # Python Claude Agent SDK

Common Mistakes

  • Skipping evaluation for Built-in Tools before production
  • No logging or tracing around claude builtin tools steps
  • Ignoring cost and latency implications

Cheat Sheet

Quick recap — the most important points from this module.

Cheat Sheet

quick ref
  • Built-in tools cover files, shell, and web-shaped work. You add custom tools for