How Instructions, Tools and MCP terms are related

#83
by jvoid - opened

Hi guys.
Talking about the instruction-tuned model term does Instruction really refer the very same thing as the Tool call. Is it just the very same thing or is it rather something near related (as instruction model would just be the more accurate for tools calling).
Or what Instruction term actually covers here?

As well when it is mentioned the model is trained for the Tool calling is this refers the very same as the MCP Tools sub concept?

Thank you

Hi,
Function call / tool call refers to a formatted output—usually in JSON—that can be parsed by a hard-coded script. For example:
{"tool": "temperature", "arguments": {"unit": "Celsius"}}
This tells the system it's time to check the temperature in Celsius.

An instruction-tuned model, compared to a pretrained model, undergoes an additional fine-tuning stage called instruction tuning, which teaches the model how to respond appropriately to questions or commands. You can think of it this way: a pretrained model might understand what a question means, but doesn't necessarily know how to respond effectively. Instruction-tuned models are trained specifically to follow prompts and provide useful outputs.
Function/tool calling is one of the capabilities often included in instruction tuning.

I'm not very familiar with MCP, but I think you're mostly right—except that some models may not follow the MCP protocol exactly.

Hi,

Great questions! Let me help clarify the distinctions and connections between these terms.

Instruction tuning : Instruction tuning refers to fine-tuning a language model to follow human-written prompts or instructions more effectively. It trains the model to behave more helpfully and safely when given tasks like:

                                       "Summarize this article"
                                      "Translate this sentence to French"
                                      "Write a function in Python"

Tool calling : Tool calling is a specific capability often layered on top of an instruction-tuned model. It allows the model to respond not just with text, but with structured outputs (usually JSON) that trigger external functions or APIs.

{ "tool": "weather_lookup", "arguments": { "location": "Paris" } }
Tool calling builds on instruction-following, but is more formalized and structured, enabling direct interaction with systems or tools.

If MCP Tools refers to a specific framework or protocol for managing tools (e.g., in a multi-agent system), then tool calling could be part of how models interface with that system.
But not all tool-calling models necessarily conform to the MCP spec.

Thank you.

Sign up or log in to comment