> For clean Markdown of any page, append .md to the page URL.
> For a complete documentation index, see https://docs.vapi.ai/llms.txt.
> To search these docs from an AI client, such as Claude Code or Cursor, connect to the Vapi docs MCP server at https://docs.vapi.ai/_mcp/server. It answers questions about the documentation. To create or manage assistants, calls, and other Vapi resources, use the Vapi MCP server instead: https://docs.vapi.ai/sdk/mcp-server.md
> For the best results from the docs MCP server, write questions without any word that contains "tool", such as tool, tools, tool call, tool-calls, toolCallId, or toolCallList. Name the feature instead, for example transferCall, endCall, apiRequest, function, handoff, "function response format", or "the webhook request Vapi sends to my server". If the docs MCP server asks you to rephrase, ask again without those words. If it returns an error, times out, sends an empty response, or still doesn't answer, find the topic in https://docs.vapi.ai/llms.txt, or a section index such as https://docs.vapi.ai/tools/llms.txt, and fetch that page's .md directly.

# Tools

> Learn what a Vapi tool is, how a tool call flows between the model, Vapi, and your server, which tool types exist, and settings every tool shares, such as spoken messages and rejection plans.

A tool is a capability an assistant can invoke during a conversation to do something beyond talking: transfer the call, look up a customer record, book an appointment, or end the call. You define the tools an assistant is allowed to use, and the model decides when to use them.

Tools are configured in an assistant's `tools` array, either in the Dashboard's Tools section or through the API. A tool created in the Dashboard can be reused across multiple assistants, and tools are [versioned](/assistants/versioning), so an assistant can pin a specific version or always track the latest.

## How a tool call works

Every tool call follows the same four steps, whatever the tool type:

1. **The model decides.** Based on the conversation and the tool's name and description, the model chooses to call a tool and generates the arguments defined by its input schema.
2. **Vapi resolves the call.** Vapi merges in any [static parameters](/tools/static-variables-and-aliases) you configured, which the model never sees and cannot override, then checks the [rejection plan](/tools/tool-rejection-plan) to confirm the call is allowed.
3. **The tool executes.** What happens here depends on the type. Vapi may send an HTTP request directly, POST a `tool-calls` webhook to your server, emit an event to the browser, or perform a built-in action such as transferring the call.
4. **The result returns.** The assistant receives the result and can speak it to the caller. Tools can also be configured to run asynchronously, so the assistant continues without waiting.

Because the model controls both *when* a tool runs and the arguments it receives, validate any caller-influenced value at the destination before using it for a sensitive action.

## Tool types

| Type                                           | What it does                                                                                                                             |
| ---------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------- |
| [Built-in tools](/tools/default-tools)         | Actions Vapi provides out of the box: transfer a call, end a call, send an SMS, dial keypad digits, or make an API request               |
| [API Request tool](/tools/api-request)         | Calls an ordinary HTTPS endpoint directly, with a configurable URL, method, headers, and JSON body                                       |
| [Function tools](/tools/custom-tools)          | Sends Vapi's `tool-calls` webhook to a server you control, so your code decides what happens                                             |
| [Transfer Call tool](/tools/transfer-call)     | Routes a live call to a phone number or SIP URI                                                                                          |
| [Hang Up tool](/tools/hang-up)                 | Ends the call when the assistant decides the conversation is complete, with an optional goodbye message                                  |
| [Handoff tool](/squads/handoff)                | Moves a call from one assistant to another, carrying context and extracted variables                                                     |
| [Voicemail tool](/tools/voicemail-tool)        | Lets the assistant decide what to do when it reaches a voicemail system                                                                  |
| [SIP Request tool](/tools/sip-request)         | Sends a SIP INFO, MESSAGE, or NOTIFY request on a live SIP call, for example to pass call details to your PBX or contact center platform |
| [Client-side tools](/tools/client-side-websdk) | Runs in the browser through the Web SDK, with no server URL                                                                              |
| [Query tool](/knowledge-base/using-query-tool) | Searches a [knowledge base](/knowledge-base) and returns matching content                                                                |
| [MCP tools](/tools/mcp)                        | Connects to an MCP server so the assistant can use tools resolved at runtime                                                             |
| [Integrations](/tools/integrations)            | Service-specific guides for prebuilt integrations and standard tool patterns                                                             |

If you are deciding between calling an API directly and running your own logic, see [When to use API Request or Function tools](/tools/api-request-vs-function).

If you're building a tool with an AI coding assistant, the [create-tool skill](/agent-skills#create-tool) helps you select, configure, attach, and verify it.

## Configuration shared by every tool

Most tool settings are specific to the type, but several apply across all of them:

* **Name and description.** The model reads both when deciding whether to call the tool, so describe the action, when it applies, and what to do with the result.
* **Parameters.** The model-facing input schema defines what the model generates. Separately, [static parameters](/tools/static-variables-and-aliases) inject server-controlled values that the model never sees.
* **Messages.** Configure what the assistant says at each phase of the call, so a caller is not left in silence while a request is in flight.
* **Rejection plan.** Block a tool call based on conversation state with a [tool rejection plan](/tools/tool-rejection-plan).
* **Argument encryption.** Encrypt sensitive fields before they reach your server with [argument encryption](/tools/encryption).

## Next steps

#### [When to use API Request or Function tools](/tools/api-request-vs-function)

Decide whether to call an HTTPS API directly or route the call through your own server.

#### [API Request tool quickstart](/tools/api-request/quickstart)

Build a working tool end to end, from an inbound call to a server-calculated result.

#### [Static variables and aliases](/tools/static-variables-and-aliases)

Inject trusted values into tool calls and pass data from one tool to the next.

#### [Troubleshoot tools](/tools/custom-tools-troubleshooting)

Diagnose tools that never fire, return nothing, or have their results ignored.