IonBin
All pages
Search
Concept

Tool use (function calling)

Tool use lets a model request operations such as retrieving an order or sending a message. Your application executes client-defined functions; providers can execute hosted tools. The surrounding system controls authorization, validation and execution. A structured request is not proof the action is appropriate.

Verified Oct 18, 2026 Review by Apr 16, 2027 2 sources

What it is

With tool use, you describe the available tools to the model: name, purpose and input fields. The model can reply with a request to call one. OpenAI calls this a multi-step conversation between your application and the model. Anthropic distinguishes client tools, which your application runs, from server tools such as web search, which Anthropic runs for you.

How it works

  1. Define tools with a name, description and input schema.
  2. The model decides a tool would help and returns a structured call with arguments.
  3. For a client-defined function, your application validates authorization and arguments, runs the operation, sends back the result and lets the model continue. Hosted tools follow the provider’s execution model.

Worked example. A support assistant has a tool lookup_order(order_id). A customer asks, “Where’s order 4471?”

  1. The model returns a call: lookup_order with order_id: "4471".
  2. Your code checks the customer owns that order, queries your store’s API and returns “shipped, arriving Thursday”.
  3. The model writes the reply.

For a second tool, refund_order, IonBin recommends an approval step unless the business has explicitly authorized a tightly bounded refund policy enforced by code.

Benefits

  • Connects models to live data and real systems.
  • Structured arguments are easier to validate than free text (see structured outputs).
  • The foundation of MCP and agent frameworks.

Limits and risks

  • The model may pick the wrong tool or the wrong arguments, so validate inputs.
  • Actions with side effects need an authorization policy, validated targets and failure handling. Use approval for consequential actions outside a preapproved scope; prevent duplicate execution when retrying.
  • Tool results can carry prompt injection.

Best-fit stacks

Stack 08

Dev, web & IT

Design, code, host and ship sites and internal tools, with an AI coding agent doing most of the typing.

Stack 06

Ops & admin automation

Hand repeat admin (receipts, logs, notices, handoffs) to workflows your agent can trigger.

Agent compatibility

Not tool-specific. See Agent-ready for connector support by tool.

Levels come from each tool's recorded, sourced compatibility. How the levels work.

Sources

  1. Function calling · OpenAIofficial accessed Oct 18, 2026
  2. Tool use with Claude · Anthropicofficial accessed Oct 18, 2026

Practitioner views are restated in our words and labeled as views, not measured results. Product facts come from official sources dated above.

Suggest an edit

IonBin's wiki isn't user-edited. Corrections go to our Directory Curator, who checks them against primary sources before anything changes. Spot something wrong or out of date on “Tool use (function calling)”? Email us with a link to a primary source.

Suggest an edit by email or write to contact@ionbin.com