# createTool()

The `createTool()` function is used to define custom tools that your Mastra agents can execute. Tools extend an agent's capabilities by allowing it to interact with external systems, perform calculations, or access specific data.

## Usage example

```typescript
import { createTool } from '@mastra/core/tools'
import { z } from 'zod'

export const tool = createTool({
  id: 'test-tool',
  description: 'Reverse the input string',
  inputSchema: z.object({
    input: z.string(),
  }),
  outputSchema: z.object({
    output: z.string(),
  }),
  execute: async inputData => {
    const reversed = inputData.input.split('').reverse().join('')

    return {
      output: reversed,
    }
  },
})
```

## Example with strict tool inputs

Set `strict: true` when you want Mastra to ask supported model providers to generate tool arguments that exactly match the tool schema.

```typescript
import { createTool } from '@mastra/core/tools'
import { z } from 'zod'

export const weatherTool = createTool({
  id: 'get-weather',
  description: 'Get weather for a city',
  strict: true,
  inputSchema: z.object({
    city: z.string(),
    units: z.enum(['metric', 'imperial']),
  }),
  execute: async ({ city, units }) => {
    return {
      city,
      units,
      forecast: 'sunny',
    }
  },
})
```

Mastra forwards `strict: true` to model adapters that support strict tool calling. On adapters that do not support strict tool calling, Mastra ignores this option.

## Example with `toModelOutput`

Use `toModelOutput` when your tool should return rich internal data to your app, but the model should receive either a simplified value or multimodal content.

```typescript
import { createTool } from '@mastra/core/tools'
import { z } from 'zod'

export const weatherTool = createTool({
  id: 'get-weather',
  description: 'Get weather for a city',
  inputSchema: z.object({
    city: z.string(),
  }),
  outputSchema: z.object({
    city: z.string(),
    temperature: z.number(),
    condition: z.string(),
    radarImageUrl: z.string().url(),
  }),
  execute: async ({ city }) => ({
    city,
    temperature: 72,
    condition: 'sunny',
    radarImageUrl: 'https://example.com/radar/seattle.png',
  }),
  toModelOutput: output => {
    return {
      type: 'content',
      value: [
        { type: 'text', text: `${output.city}: ${output.temperature}F and ${output.condition}` },
        { type: 'image-url', url: output.radarImageUrl },
      ],
    }
  },
})
```

The tool still returns the full `execute` result to your application, while the model receives the transformed `toModelOutput` value.

`toModelOutput` can return:

- `type: 'text'`
- `type: 'json'`
- `type: 'content'` with parts like `text`, `image-url`, `image-data`, `file-url`, `file-data`, `file-id`, `image-file-id`, or `custom`

## Example with MCP annotations

When exposing tools via MCP (Model Context Protocol), you can add annotations to describe tool behavior and customize how clients display the tool. These MCP-specific properties are grouped under the `mcp` property:

```typescript
import { createTool } from '@mastra/core/tools'
import { z } from 'zod'

export const weatherTool = createTool({
  id: 'get-weather',
  description: 'Get current weather for a location',
  inputSchema: z.object({
    location: z.string().describe('City name or coordinates'),
  }),
  // MCP-specific properties
  mcp: {
    // Annotations for client behavior hints
    annotations: {
      title: 'Weather Lookup', // Human-readable display name
      readOnlyHint: true, // Tool doesn't modify environment
      destructiveHint: false, // Tool doesn't perform destructive updates
      idempotentHint: true, // Same args = same result
      openWorldHint: true, // Interacts with external API
    },
    // Custom metadata for client-specific functionality
    _meta: {
      version: '1.0.0',
      category: 'weather',
    },
  },
  execute: async inputData => {
    const weather = await fetchWeather(inputData.location)
    return { weather }
  },
})
```

## Parameters

**id** (`string`): A unique identifier for the tool.

**description** (`string`): A description of what the tool does. This is used by the agent to decide when to use the tool.

**inputSchema** (`Zod schema`): A Zod schema defining the expected input parameters for the tool's \`execute\` function.

**outputSchema** (`Zod schema`): A Zod schema defining the expected output structure of the tool's \`execute\` function.

**strict** (`boolean`): When true, Mastra enables strict tool input generation on model adapters that support it. This helps supported providers return arguments that match the tool schema more closely.

**toModelOutput** (`(output: TSchemaOut) => unknown`): Optional function that transforms the tool's \`execute\` output before it is sent back to the model. Use this to return \`text\`, \`json\`, or \`content\`-shaped outputs (including multimodal parts like images/files) to the model while still keeping the full raw output in your application code.

**suspendSchema** (`Zod schema`): A Zod schema defining the structure of the payload passed to \`suspend()\`. This payload is returned to the client when the tool suspends execution.

**resumeSchema** (`Zod schema`): A Zod schema defining the expected structure of \`resumeData\` when the tool is resumed. Used by the agent to extract data from user messages when \`autoResumeSuspendedTools\` is enabled.

**requireApproval** (`boolean`): When true, the tool requires explicit approval before execution. The agent will emit a \`tool-call-approval\` chunk and pause until approved or declined.

**mcp** (`MCPToolProperties`): MCP-specific properties for tools exposed via Model Context Protocol. Includes \`annotations\` (tool behavior hints like \`title\`, \`readOnlyHint\`, \`destructiveHint\`, \`idempotentHint\`, \`openWorldHint\`) and \`\_meta\` (arbitrary metadata passed through to MCP clients).

**requestContextSchema** (`Zod schema`): A Zod schema for validating request context values. When provided, the context is validated before execute() runs, returning an error object if validation fails.

**execute** (`function`): The function that contains the tool's logic. It receives two parameters: the validated input data (first parameter) and an optional execution context object (second parameter) containing \`requestContext\`, \`tracingContext\`, \`abortSignal\`, and other execution metadata.

**execute.input** (`z.infer<TInput>`): The validated input data based on inputSchema

**execute.context** (`ToolExecutionContext`): Optional execution context containing metadata

**execute.context.requestContext** (`RequestContext`): Request Context for accessing shared state and dependencies

**execute.context.tracingContext** (`TracingContext`): Tracing context for creating child spans and adding metadata

**execute.context.abortSignal** (`AbortSignal`): Signal for aborting the tool execution

**execute.context.agent** (`AgentToolExecutionContext`): Agent-specific context, available when the tool is executed by an agent.

**execute.context.workflow** (`WorkflowToolExecutionContext`): Workflow-specific context (state, setState, suspend, etc.)

**execute.context.mcp** (`MCPToolExecutionContext`): MCP-specific context (elicitation, etc.)

**onInputStart** (`function`): Optional callback invoked when the tool call input streaming begins. Receives \`toolCallId\`, \`messages\`, and \`abortSignal\`.

**onInputDelta** (`function`): Optional callback invoked for each incremental chunk of input text as it streams in. Receives \`inputTextDelta\`, \`toolCallId\`, \`messages\`, and \`abortSignal\`.

**onInputAvailable** (`function`): Optional callback invoked when the complete tool input is available and parsed. Receives the validated \`input\` object, \`toolCallId\`, \`messages\`, and \`abortSignal\`.

**onOutput** (`function`): Optional callback invoked after the tool has successfully executed and returned output. Receives the tool's \`output\`, \`toolCallId\`, \`messages\`, and \`abortSignal\`.

## Returns

The `createTool()` function returns a `Tool` object.

**Tool** (`object`): An object representing the defined tool, ready to be added to an agent.

## Tool lifecycle hooks

Tools support lifecycle hooks that allow you to monitor and react to different stages of tool execution. These hooks are particularly useful for logging, analytics, validation, and real-time updates during streaming.

### Available Hooks

#### `onInputStart`

Called when tool call input streaming begins, before any input data is received.

```typescript
export const tool = createTool({
  id: 'example-tool',
  description: 'Example tool with hooks',
  onInputStart: ({ toolCallId, messages, abortSignal }) => {
    console.log(`Tool ${toolCallId} input streaming started`)
  },
})
```

#### `onInputDelta`

Called for each incremental chunk of input text as it streams in. Useful for showing real-time progress or parsing partial JSON.

```typescript
export const tool = createTool({
  id: 'example-tool',
  description: 'Example tool with hooks',
  onInputDelta: ({ inputTextDelta, toolCallId, messages, abortSignal }) => {
    console.log(`Received input chunk: ${inputTextDelta}`)
  },
})
```

#### `onInputAvailable`

Called when the complete tool input is available and has been parsed and validated against the `inputSchema`.

```typescript
export const tool = createTool({
  id: 'example-tool',
  description: 'Example tool with hooks',
  inputSchema: z.object({
    city: z.string(),
  }),
  onInputAvailable: ({ input, toolCallId, messages, abortSignal }) => {
    console.log(`Tool received complete input:`, input)
    // input is fully typed based on inputSchema
  },
})
```

#### `onOutput`

Called after the tool has successfully executed and returned output. Useful for logging results, triggering follow-up actions, or analytics.

```typescript
export const tool = createTool({
  id: 'example-tool',
  description: 'Example tool with hooks',
  outputSchema: z.object({
    result: z.string(),
  }),
  execute: async input => {
    return { result: 'Success' }
  },
  onOutput: ({ output, toolCallId, toolName, abortSignal }) => {
    console.log(`${toolName} execution completed:`, output)
    // output is fully typed based on outputSchema
  },
})
```

### Hook Execution Order

For a typical streaming tool call, the hooks are invoked in this order:

1. **onInputStart**: Input streaming begins
2. **onInputDelta**: Called multiple times as chunks arrive
3. **onInputAvailable**: Complete input is parsed and validated
4. Tool's **execute** function runs
5. **onOutput**: Tool has completed successfully

### Hook Parameters

All hooks receive a parameter object with these common properties:

- `toolCallId` (string): Unique identifier for this specific tool call
- `abortSignal` (AbortSignal): Signal for detecting if the operation should be cancelled

Additionally:

- `onInputStart`, `onInputDelta`, and `onInputAvailable` receive `messages` (array): The conversation messages at the time of the tool call
- `onInputDelta` receives `inputTextDelta` (string): The incremental text chunk
- `onInputAvailable` receives `input`: The validated input data (typed according to `inputSchema`)
- `onOutput` receives `output`: The tool's return value (typed according to `outputSchema`) and `toolName` (string): The name of the tool

### Error handling

Hook errors are caught and logged automatically, but don't prevent tool execution from continuing. If a hook throws an error, it will be logged to the console but won't fail the tool call.

## MCP tool annotations

When exposing tools via the Model Context Protocol (MCP), you can provide annotations that describe tool behavior. These annotations help MCP clients like OpenAI Apps SDK understand how to present and handle your tools.

MCP-specific properties are grouped under the `mcp` property, which includes `annotations` and `_meta`:

```typescript
mcp: {
  annotations: { /* behavior hints */ },
  _meta: { /* custom metadata */ },
}
```

### `ToolAnnotations` Properties

**title** (`string`): A human-readable title for the tool. Used for display purposes in UI components.

**readOnlyHint** (`boolean`): If true, the tool does not modify its environment. This hint indicates the tool only reads data and has no side effects. Defaults to false.

**destructiveHint** (`boolean`): If true, the tool may perform destructive updates to its environment. If false, the tool performs only additive updates. This hint helps clients determine if confirmation should be required. Defaults to true.

**idempotentHint** (`boolean`): If true, calling the tool repeatedly with the same arguments will have no additional effect on its environment. This hint indicates idempotent behavior. Defaults to false.

**openWorldHint** (`boolean`): If true, this tool may interact with an 'open world' of external entities (e.g., web search, external APIs). If false, the tool's domain is closed and fully defined. Defaults to true.

These annotations follow the [MCP specification](https://spec.modelcontextprotocol.io/specification/2025-03-26/server/tools/#tool-annotations) and are passed through when tools are listed via MCP.

## Related

- [MCP Overview](https://mastra.ai/docs/mcp/overview)
- [Using Tools with Agents](https://mastra.ai/docs/agents/using-tools)
- [Agent Approval](https://mastra.ai/docs/agents/agent-approval)
- [Tool Streaming](https://mastra.ai/docs/streaming/tool-streaming)
- [Request Context](https://mastra.ai/docs/server/request-context)