Back
advanced
AI Agents & Autonomous Systems

Tool Use, Function Calling, and Computer Use

Design tool-calling systems with schemas, permissions, validation, observations, and safe action boundaries

25 min read· Function Calling· Tool Use· OpenAI API· AI Agents

Tool Use, Function Calling, and Computer Use

Tool use lets a model ask software to do work.

The model should not directly execute arbitrary actions. It should request a typed tool call, and your app decides whether to run it.

Tool-call loop

text
user goal -> model chooses tool -> app validates args -> tool runs -> model observes result -> final answer

Good tool design

Each tool needs:

  • clear name
  • narrow purpose
  • typed arguments
  • validation rules
  • permission checks
  • safe error messages
  • audit logging

Function calling vs computer use

Tool styleBest for
API/function callreliable structured systems
MCP toolreusable cross-client tools
browser/computer usesystems without APIs

Prefer APIs when available. Use computer use only when the UI is the interface.

Risky tools need approval

Require approval for:

  • sending email
  • deleting data
  • spending money
  • changing permissions
  • deploying code
  • accessing sensitive records

Knowledge check

Q1: Who should validate tool arguments?

Your application, not only the model.

Q2: Why are narrow tools safer?

They limit what the model can ask the system to do.