Agents5 min read
Tool Calling and AI Agents: How Function Calling Really Works
How LLM tool calling works, how to write tool descriptions models use correctly, how agent loops run and stop, and the failures to plan for in agents.
Tools & agents
Tool calling and AI agents: prompting models that act
Tool calling lets a model request an action, such as searching, reading a file or calling an API, by returning a structured call that your code executes. An AI agent repeats that loop until the task is done. Prompting here is mostly about clear tool names and descriptions, precise parameters, and rules for when to act, when to ask and when to stop.
Coming soon onApp StoreComing soon onGoogle Play
Structured outputIntermediate
Your app parses the model’s JSON, but sometimes the reply starts with “Sure! Here is the JSON:”. What is the most robust fix?
AAdd “please” to the prompt
BUse structured-output mode with a schema, then validate
CLower the temperature to 0
DStrip the first line of every reply
Sample question · Tools & agents
An agent keeps calling the same search tool in a loop. Which change helps most?
- ARaise the token limit
- BDescribe when the tool is useful, and add a stop rule such as a max number of searches before answering
- CRemove the tool description to save tokens
- DAsk the model to be faster
Show the answer and why
B. Describe when the tool is useful, and add a stop rule such as a max number of searches before answering Agents decide from tool descriptions and stop conditions. Without a clear purpose and a limit, repeating the call looks as reasonable to the model as stopping.
What the questions test
- Writing tool names and descriptions a model can choose from
- Parameter design and input validation
- Stop conditions and step limits
- Asking for confirmation before risky actions
What you’ll learn
- How function calling works end to end
- How to describe tools so the model picks the right one
- How agent loops fail and how to bound them
- Where a human should stay in the loop
How to practice it in TokIQ
- 1. Open Tools & agents. Pick it from the topic list on the Quiz tab. It is a Premium topic; the free plan includes Fundamentals, Role & context and Examples.
- 2. Answer one question at a time. You see right away whether you were correct.
- 3. Tap Why? Read the short explanation and answer three follow-up questions on the same idea.
- 4. Watch your accuracy. The Progress tab shows how Tools & agents compares with your other topics.
Tools & agents: common questions
What is tool calling (function calling) in LLMs?
Tool calling is when the model returns a structured request to run a function you defined, with arguments. Your code runs it and sends the result back, and the model continues with that result.
What is the difference between a chatbot and an AI agent?
A chatbot replies to messages. An agent can call tools in a loop, deciding its next step from each result, until it reaches a goal or a stop condition.
Further reading
Safety6 min read
Prompt Injection Explained: Direct vs Indirect Attacks and Fixes
Prompt injection tricks an AI into following attacker instructions hidden in input or documents. Learn direct vs indirect attacks and the mitigations that work.
Output5 min read
How to Get Reliable JSON From LLMs: Schemas, Validation, Retries
Getting valid JSON from an LLM takes more than asking nicely. Use schemas, structured output modes, validation and retries, and avoid the usual failure modes.
More topics
Practice tools & agents a few questions a day.
Short quizzes on real prompting decisions, with an explanation for every answer. Free to start on iPhone and Android.
Coming soon onApp StoreComing soon onGoogle Play