# Built-in tools: Read, Write, Edit, Bash, Grep, Glob

*Claude Certified Architect - Foundations Study Guide · Tool Design & MCP Integration · Last updated October 22, 2026 · https://www.certifyforce.com/study-guide/claude-certified-architect-foundations/tool-design-and-mcp-integration/built-in-tools-read-write-edit-bash-grep-glob*

Grep for file contents versus Glob for file paths, Read with offset and limit for large files, Edit's unique-match rule and the Read + Write fallback, incremental exploration from Grep entry points, tracing wrapper modules by exported name, and why Glob and Grep may be absent by default.

- Certification: Claude Certified Architect - Foundations
- Exam section: Tool Design & MCP Integration
- Study guide: https://www.certifyforce.com/study-guide/claude-certified-architect-foundations

**Official exam objective:**

> Select and apply built-in tools (Read, Write, Edit, Bash, Grep, Glob) effectively

## What the exam expects

- Select Grep to search file contents (callers of a function, error messages, import statements) and Glob to find files by path pattern such as `**/*.test.tsx`.
- Use Read and Write for whole-file operations and Edit for targeted changes anchored on unique text.
- Recover when Edit fails on a non-unique match: widen the anchor, or Read the full file and Write the complete corrected content.
- Build codebase understanding incrementally (Grep for entry points, Read and follow imports) instead of reading every file upfront, and trace usage through wrapper modules by searching every exported name.
- Know Bash's role and that Glob and Grep are not in Claude Code's default tool set on macOS, Linux and WSL.

Key terms: **Grep** (searches inside files); **Glob** (matches file paths); **Edit** (exact replacement of a unique `old_string`); **Write** (creates or overwrites a whole file); **entry point** (where a targeted search lands before you follow imports); **wrapper module** (re-exports or wraps a function under other names).

## Key facts

| Fact | Detail | Source |
|---|---|---|
| Grep output modes | `files_with_matches` (default, paths), `content` (lines with line numbers), `count` | [Tools reference](https://code.claude.com/docs/en/tools-reference) |
| Grep and `.gitignore` | Gitignored files skipped; pass the path to search one | [Tools reference](https://code.claude.com/docs/en/tools-reference) |
| Glob results | Sorted by modification time, capped at 100 files | [Tools reference](https://code.claude.com/docs/en/tools-reference) |
| Edit matching | Exact string, no regex or fuzzy matching; must appear exactly once | [Tools reference](https://code.claude.com/docs/en/tools-reference) |
| Edit non-unique options | Longer `old_string` or `replace_all: true` (replaces all) | [Tools reference](https://code.claude.com/docs/en/tools-reference) |
| Write | Creates or overwrites with full content; never appends or merges | [Tools reference](https://code.claude.com/docs/en/tools-reference) |
| Read limits | 25,000 tokens per call by default; whole file over 256 KB refused; use `offset`/`limit` | [Tools reference](https://code.claude.com/docs/en/tools-reference) |
| Default tool set | Glob and Grep absent on macOS, Linux, WSL unless named | [Tools reference](https://code.claude.com/docs/en/tools-reference) |
| Non-unique Edit fallback | Read full file, Write complete content | [Exam guide](https://everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F6nizmqk8tpzpfjvt6qmmav7rh%2Fpublic%2F1783542750%2FClaude+Certified+Architect+%E2%80%93+Foundations+Exam+Guide.pdf) |

## Check yourself

- Why does Glob suit `db/**/*.migration.sql` while Grep suits finding `import legacy_auth`?
- When should an agent switch from Edit to Read plus Write?
- What should an agent do when Read refuses a 40 MB log as too large?
- Why might a Claude Code session on Linux search with Bash `grep` instead of the Grep tool?

## Sources

- [Tools reference](https://code.claude.com/docs/en/tools-reference)
- [Claude Certified Architect – Foundations Exam Guide v1.0](https://everpath-course-content.s3-accelerate.amazonaws.com/instructor%2F6nizmqk8tpzpfjvt6qmmav7rh%2Fpublic%2F1783542750%2FClaude+Certified+Architect+%E2%80%93+Foundations+Exam+Guide.pdf)
- [Effective context engineering for AI agents](https://www.anthropic.com/research/effective-context-engineering-for-ai-agents)
- [Common workflows](https://code.claude.com/docs/en/common-workflows)
- [Best practices for Claude Code](https://code.claude.com/docs/en/best-practices)
- [Agent SDK overview](https://code.claude.com/docs/en/agent-sdk/overview)

## About the full unit

The "Core concepts", "Exam traps" and "Worked scenario" sections of this unit, its 11 linked practice questions, and unlimited timed mock exams are included with the Claude Certified Architect - Foundations pack (USD $19): https://www.certifyforce.com/practice-exams