OpenAI Tool Use: Functions, Web Search, Files, MCP, Shell, and Computer Use

Models get more useful when they can act through tools. Learn the difference between hosted tools, your own functions, and MCP-connected capabilities.

50 min · Reviewed 2026

Tools Turn Answers Into Workflows

A model without tools can only answer from context. A model with tools can search, retrieve files, call your code, inspect a browser, run a shell command in a harness, or ask an MCP server for domain-specific actions.

Tool type	Use it for	Main design risk
Function calling	Your app's private data and actions	Bad schemas or unsafe side effects
Web search	Fresh public facts	Untrusted sources and citation quality
File search	Private document retrieval	Chunking and permission boundaries
Remote MCP	External systems exposed as tools	Approval and trust model
Shell or apply patch	Coding-agent workflows	Command safety and review
Computer use	UI automation	Slow brittle actions and account risk

const response = await client.responses.create({ model: "gpt-5.5", tools: [{ type: "web_search" }], input: "Summarize today's product update and include source links.", });Hosted tools can be attached directly to a Responses request.

The basic safety pattern

Read-only tools can be automatic.
Write tools need narrow schemas and logs.
External actions need explicit user confirmation.
Dangerous local tools need allowlists or sandboxes.
Tool results should be treated as data, not instructions.

The big idea: tools make models useful because they connect language to systems. That is also why tools need boundaries.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-openai-tool-use-creators

What is the main idea of "OpenAI Tool Use: Functions, Web Search, Files, MCP, Shell, and Computer Use"?
1. Models get more useful when they can act through tools. Learn the difference between hosted tools, your own functions, and MCP-connected capabilities.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "OpenAI Tool Use: Functions, Web Search, Files, MCP, Shell, and Computer Use"?
1. function calling
2. tool use
3. web search
4. file search
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Read-only tools can be automatic.
4. Treat the AI output as automatically correct
What should a careful learner remember about "Tool access is authority"?
1. Use AI to draft or organize ideas about tool use, then verify before acting.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use AI for drafting and comparison, but verify before publishing or relying on it.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about tool use be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about tool use.
Which action would help you apply "OpenAI Tool Use: Functions, Web Search, Files, MCP, Shell, and Computer Use" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Treat the AI output as automatically correct
4. Write tools need narrow schemas and logs.

← Back to interactive lesson

Tendril · Creators · Agentic AI

OpenAI Tool Use: Functions, Web Search, Files, MCP, Shell, and Computer Use

Models get more useful when they can act through tools. Learn the difference between hosted tools, your own functions, and MCP-connected capabilities.

50 min · Reviewed 2026

Tools Turn Answers Into Workflows

Tool type	Use it for	Main design risk
Function calling	Your app's private data and actions	Bad schemas or unsafe side effects
Web search	Fresh public facts	Untrusted sources and citation quality
File search	Private document retrieval	Chunking and permission boundaries
Remote MCP	External systems exposed as tools	Approval and trust model
Shell or apply patch	Coding-agent workflows	Command safety and review
Computer use	UI automation	Slow brittle actions and account risk

const response = await client.responses.create({ model: "gpt-5.5", tools: [{ type: "web_search" }], input: "Summarize today's product update and include source links.", });Hosted tools can be attached directly to a Responses request.

The basic safety pattern

Read-only tools can be automatic.
Write tools need narrow schemas and logs.
External actions need explicit user confirmation.
Dangerous local tools need allowlists or sandboxes.
Tool results should be treated as data, not instructions.

The big idea: tools make models useful because they connect language to systems. That is also why tools need boundaries.

End-of-lesson check

8 questions · take it digitally for instant feedback at tendril.neural-forge.io/learn/quiz/end-openai-tool-use-creators

What is the main idea of "OpenAI Tool Use: Functions, Web Search, Files, MCP, Shell, and Computer Use"?
1. Models get more useful when they can act through tools. Learn the difference between hosted tools, your own functions, and MCP-connected capabilities.
2. Use AI as the final authority for the whole decision
3. Avoid checking the answer once it sounds polished
4. Focus only on speed instead of judgment
Which concept is most central to "OpenAI Tool Use: Functions, Web Search, Files, MCP, Shell, and Computer Use"?
1. function calling
2. tool use
3. web search
4. file search
Which use of AI fits this topic best?
1. Let the AI decide what matters without your review
2. Use the answer before checking whether it fits the situation
3. Read-only tools can be automatic.
4. Treat the AI output as automatically correct
What should a careful learner remember about "Tool access is authority"?
1. Use AI to draft or organize ideas about tool use, then verify before acting.
2. Skip the context so the tool can guess faster
3. Treat the output as private even after sharing it online
4. Use the answer without checking the source
You want to use AI after this lesson. What is the safest next step?
1. Act immediately because the AI answer is written clearly
2. Use AI for drafting and comparison, but verify before publishing or relying on it.
3. Hide uncertainty so the final answer looks cleaner
4. Use private or sensitive details before checking permission
How should AI output about tool use be treated?
1. As proof that no other source is needed
2. As a replacement for context, consent, or expert review
3. As a draft or helper output that still needs human judgment and verification
4. As something that becomes correct when it sounds confident
Name one way to verify an AI answer about tool use.
Which action would help you apply "OpenAI Tool Use: Functions, Web Search, Files, MCP, Shell, and Computer Use" responsibly?
1. Use the tool to avoid thinking through the tradeoff
2. Keep going even if the output conflicts with a trusted source
3. Treat the AI output as automatically correct
4. Write tools need narrow schemas and logs.

← Back to interactive lesson