Definition
Tool calling lets a language model ask software to run a function, such as a search, calculation or database update, and then use the result.
Tool calling explained
Language models can't look up live data or change systems on their own. With tool calling, developers describe the tools available, each with a name, a description and the inputs it accepts. When the model decides a tool would help, it outputs a structured request, the application runs the tool, and the result is passed back so the model can continue.
Tools can be almost anything:
- Looking up an order, customer or product in a database.
- Searching the web or an internal knowledge base.
- Doing reliable arithmetic or date calculations.
- Creating a calendar event, ticket or CRM task.
- Sending a draft for human approval.
Tool calling is what turns a language model into an agent. Reliability comes from clear tool descriptions, strict validation of inputs, sensible error messages the model can act on, and permission checks in the tool itself rather than trusting the model to behave.
Example
A customer asks your support assistant “where is my order?”. The model calls an order-lookup tool with the customer's order number, receives the tracking status, and replies with the real delivery date instead of generic shipping information.
Why it matters
Tool calling is how AI moves from giving advice to doing work, using your real data and systems.
Related service
Agentic AI Tools
Custom AI agents and automations that connect to your data and tools, with a human in the loop.
Custom agentic AI toolsPublished by Vidern, founded and led by Malhar Shah. Updated .
Have a process an AI agent could run?
Describe the workflow and we'll reply within 1 business day with what we'd build.
Related terms
- AI agentAn AI agent is software that uses a language model to choose and take actions, such as searching, reading files or updating systems, to finish a task.
- MCP (Model Context Protocol)MCP (Model Context Protocol) is an open standard for connecting AI applications to external data sources, tools and workflows through a common interface.
- Agentic AIAgentic AI is AI that works toward a goal over several steps, deciding what to do next and using tools such as search, databases and apps.
- RAG (Retrieval-Augmented Generation)RAG (retrieval-augmented generation) is when an AI system first retrieves relevant documents, then has a language model write its answer from them.