Key points
- Tool use is when a model does not answer alone and instead reaches for outside means to get the job done.
- There are things a model cannot do: today's news, exact arithmetic, opening your own files, anything that happens out in the world.
- The real work is deciding what to use, and what not to. Pick wrong, and the whole result comes out sideways.
- Handing it off is not the end. Looking at the result and deciding what's next is part of the loop too.
- Function calling and tool use are often used almost interchangeably. If you split them, function calling focuses more on the form for calling, and tool use more on when and how to use it.
The analogy
Say you are reheating a bag of frozen dumplings. The kitchen has a microwave, an air fryer, and a steamer. Which one you pick changes the result completely. Want it fast, use the microwave. Want the outside crisp, use the air fryer. Want it soft and moist, use the steamer.
Once you pick, you set the time and press start. That is not the end, either. When it is done, you open it up and check, and if the middle is still cold, you run it a little longer. And on days you are fine eating straight from the bag, you do not reach for any of them.
Deciding what to hand the job to, handing it off, checking the result, and deciding again: that whole loop is tool use.
In detail
Why hand it a means at all
A model is extremely good at continuing text based on what it has learned. What it cannot do is a separate matter. It has never learned about something that happened yesterday, long arithmetic tends to drift when done by continuing text, and it has simply never seen the document sitting in your own drawer.
Anything happening out in the world is even further out of reach. Sending an email or booking an appointment does not happen just because a sentence describing it was written well. However well-crafted the words, they do not turn into an email on their own.
So it gets handed a means: a way to look things up, a way to calculate, a way to open a document, a way to actually carry something out. It is a way of splitting what it is good at from what it is not, and pushing the parts it is not good at outward.
Deciding what to use
Handing over several means does not automatically mean it uses them well. It has to judge whether this question needs a means at all, and if so, which one. That judgment is half of what tool use actually is.
Pick wrong and the whole result wobbles. Sometimes it slows itself down looking things up when it already knew the answer; other times it makes something up on the spot when it should have looked something up instead. Either way, it can look just as convincing to a person reading it, which makes the mistake hard to catch.
Having more means to choose from actually makes choosing harder, the same way ten different appliances in a kitchen just gets confusing. Each means needs a short, clear description of exactly what it is for, or the picking goes wrong more often.
Taking the result and continuing
Handing something off gets a result back. That result does not automatically become the answer. The model reads what came back, weighs it against the question, and pulls together only the part it needs into a sentence.
One more judgment call happens right here. If the result comes back empty or off-target, it has to try again: rephrase the search and look again, switch to a different means, or just say plainly that it could not find anything. It is the same as opening the dumplings back up and running them a little longer if the middle is still cold.
The fact that this loop can run more than once matters too. Some things finish in one pass; others keep going, where a search result leads to another search.
Calling something and using it differ in scope
There is a narrower, plainer idea sitting next to this one: the fixed, agreed way of calling a means. That one is about the calling convention — each means has a name, a fixed shape for what goes in, and a fixed shape for what comes back out. Think of it as the procedure for filling out a form and handing it over.
The two terms are close enough that they often get mixed together. If function calling puts its focus on the form being called and the call itself, tool use is the wider term that also covers when to pull it out, whether to trust what comes back, and what to do next.
Push this one step further and it becomes an agent. That is when the loop of reaching for means runs on for a long while. For things that cannot be undone, a person's confirmation is often required from the very first call.
More precisely
Reaching for a means does not mean the model physically does anything itself. What actually happens is it writes out a description of what means to call and how, an outside program reads that and carries it out on its behalf, and the result gets handed back to the model. From start to finish, the model only trades requests and results and never runs anything itself. The result is often text, but something like a screen capture image can come back too.
The kitchen comparison breaks down somewhere too. A person can see and tell when a dumpling is undercooked; a model has a much harder time checking on its own whether the text that came back is actually correct. It can end up trusting and carrying forward a wrong value a means handed it. A broken appliance at least shows some sign of it; a means can quietly hand back a wrong value with no sign at all.
It is worth noting, too, that handing over a means is really handing over permission. A means that only reads and one that changes something carry very different stakes when they go wrong. That is why, when attaching a means, what it is allowed to do usually gets narrowed down to exactly what is needed, alongside a log of what got called and when.
Try it yourself
- Perplexity (AI search) ailearn.space In the default "검색" (Search), the source numbers on the answer and the source list show what it went and found. Press "/" in the input box and pick "심층 리서치" (Deep Research) to also watch it search and read repeatedly as it pulls things together
- NotebookLM (AI notes from your own material) ailearn.space Compare how the evidence behind an answer changes once it gains a way to open the material you uploaded
- Ai2 Playground (try open models) ailearn.space Before starting a chat, turn on "Enable" next to "This model allows tool calling", add the example "getWeather" under "Add or edit tools", then ask about the weather in English. Instead of answering directly, the model calls the tool and writes out the values to pass it, and once you type a result into the "Enter tool response:" box, it takes that and continues its answer
Common misconceptions
It's easy to think attaching a means makes the model smarter, but actually the model stays the same — what widens is the range of things it can get done.
It's easy to think a result that comes back is always correct, but actually it can come back empty or wrong, and trusting it and moving on regardless is a common failure.
It's easy to think more is always better, but actually the more there are to choose from, the more often the wrong one gets picked.
One-line summary
Tool use is handing off what a model cannot do to an outside means and continuing from the result, and the judgment behind what to use is what separates it.
Spotted an error or have a better analogy? Suggest an edit · Last updated 2026-10-18