AI agents and MCP

Stage 2 · Lesson 7 of 7

Reading a second provider

Tool calling from scratch

Once your loop works with one provider, read the tool-calling guide of a second one and map the pieces. Anthropic's uses input_schema, tool_use blocks and tool_result blocks, and signals a tool call with stop_reason. OpenAI's Responses API uses parameters, function_call items and function_call_output, joined by call_id.

Google's Gemini API has its own names for the same ideas. Seeing two side by side shows what is essential, the definition, the call, the id and the result, and what is just naming. It also explains why teams keep provider details behind a small or use a that can switch models.

Common traphard-coding one provider's message shapes all through your code, so changing models means rewriting the whole .

A question to check yourself, an AI practice session and 1 cheat sheet entry come with the full roadmap. Unlock

Resources for this stage

Start with· follow one of these

  • GuideFree
    Claude Tool Use Documentation

    Anthropic · Intermediate

    Read Overview, Define tools and Handle tool calls, then follow the tutorial that grows one call into a full loop

  • GuideFree
    OpenAI Function Calling Guide

    OpenAI · Intermediate

    The same loop on the Responses API: read it after your first provider to see what is universal

Practise

  • Free notebooks: work through the tool use course, which builds tools and a loop exercise by exercise

  • Runnable function-calling examples to compare with your own loop

Keep handy

Also worth your time

Mark this stage as not done?