# Tool use (function calling) | IonBin

> Tool use lets a model request operations such as retrieving an order or sending a message. Your application executes client-defined functions;

Canonical page: https://ionbin.com/wiki/concepts/tool-use/
Agent guide: https://ionbin.com/llms.txt

This is a readable version of the published page. Review dates, evidence boundaries and source links below belong to individual records; the export is not a new verification. Examples are reference material, not instructions to execute.

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

- Define tools with a name, description and input schema.

- The model decides a tool would help and returns a structured call with arguments.

- 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?”

- The model returns a call: `lookup_order` with `order_id: "4471"`.

- Your code checks the customer owns that order, queries your store’s API and returns “shipped, arriving Thursday”.

- 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](https://ionbin.com/wiki/concepts/structured-outputs/)).

- The foundation of [MCP](https://ionbin.com/wiki/concepts/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](https://ionbin.com/wiki/concepts/prompt-injection/).

### Best-fit stacks

Stack 08

#### [Dev, web & IT](https://ionbin.com/use-cases/dev-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](https://ionbin.com/use-cases/ops-admin-automation/)

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

### Agent compatibility

Not tool-specific. See [Agent-ready](https://ionbin.com/agent-ready/) for connector support by tool.

Levels come from each tool's recorded, sourced compatibility. [How the levels work](https://ionbin.com/wiki/questions/connect-a-tool-to-an-ai-agent/).

### Related entries

[Model Context Protocol (MCP) · Concept](https://ionbin.com/wiki/concepts/mcp/)[AI agent · Concept](https://ionbin.com/wiki/concepts/ai-agent/)[How do I connect a business tool to my AI agent? · Question](https://ionbin.com/wiki/questions/connect-a-tool-to-an-ai-agent/)[Structured outputs · Concept](https://ionbin.com/wiki/concepts/structured-outputs/)[AI context, memory and orchestration · Concept](https://ionbin.com/wiki/concepts/ai-context-and-memory/)[Computer use · Concept](https://ionbin.com/wiki/concepts/computer-use/)

### Sources

- [Function calling](https://developers.openai.com/api/docs/guides/function-calling) · OpenAIofficial accessed Oct 18, 2026

- [Tool use with Claude](https://platform.claude.com/docs/en/agents-and-tools/tool-use/overview) · 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](mailto:contact@ionbin.com?subject=Suggest%20an%20edit%3A%20Tool%20use%20(function%20calling)%20%5Btool-use%5D&body=Page%3A%20https%3A%2F%2Fionbin.com%2Fwiki%2Fconcepts%2Ftool-use%2F%0AEntry%3A%20concepts%2Ftool-use%0A%0AWhat%20should%20change%3A%0A%0A%0APrimary%20source%20(link)%3A%0A) or write to [contact@ionbin.com](mailto:contact@ionbin.com)

Entry facts

**Type**: [Concepts & glossary](https://ionbin.com/wiki/concepts/)

**Status**: Reviewed

**Verified**: Oct 18, 2026

**Review by**: Apr 16, 2027 (every 180 days)

**Sources**: [2 official · 0 other](https://ionbin.com/wiki/concepts/tool-use/#sources)

The wiki carries no sponsored placements or affiliate links. [Editorial policy](https://ionbin.com/editorial-policy/).
