> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.cohere.com/v1/docs/tools/llms.txt.
> For AI client integration (Claude Code, Cursor, etc.), connect to the MCP server at https://docs.cohere.com/_mcp/server.

# An Overview of Tool Use with Cohere

> Understand single-step and multi-step tool use, and learn when to use each in your workflows.

Here, you'll find context on [single-step tool use](/docs/tool-use) and [multi-step tool use](/docs/multi-step-tool-use).

Single-step is sometimes referred to as "function calling" because it uses functions to call external tools that augment the capabilities of large language models. Multi-step tool use is sometimes referred to as "agents," because it forms the core of many workflows relying on agents.

You'll also find additional documentation on the various [types of parameters](/docs/parameter-types-in-tool-use) offered by Cohere's tool use functionality, as well as a guide on when to use single-step v.s. multi-step capabilities.

> Cohere's API documentation helps developers easily integrate natural language processing and generation into their products.

## Docs

- [Multi-step Tool Use (Agents)](https://docs.cohere.com/v1/docs/multi-step-tool-use.md): "Cohere's tool use feature enhances AI capabilities by connecting external tools for dynamic, adaptable, and sequential actions."
- [Implementing a Multi-Step Agent with Langchain](https://docs.cohere.com/v1/docs/implementing-a-multi-step-agent-with-langchain.md): This page describes how to building a powerful, flexible AI agent with Cohere and LangChain. (V1)
- [How Does Single-Step Tool Use Work?](https://docs.cohere.com/v1/docs/tool-use.md): Enable your large language models to connect with external tools for more advanced and dynamic interactions (V1).
- [What Parameter Types are Available in Tool Use?](https://docs.cohere.com/v1/docs/parameter-types-in-tool-use.md): This page describes Cohere's tool use parameters and how to work with them.