makeAssistantTool creates a React component that provides a tool to the assistant. This is useful for defining reusable tools that can be composed into your application.

Usage#

import { makeAssistantTool, tool } from "@assistant-ui/react";
import { z } from "zod";

// Define the tool using the tool() helper
const submitForm = tool({
  parameters: z.object({
    email: z.string().email(),
    name: z.string(),
  }),
  execute: async ({ email, name }) => {
    // Implementation
    return { success: true };
  },
});

// Create a tool component
const SubmitFormTool = makeAssistantTool({
  ...submitForm,
  toolName: "submitForm",
});

// Use in your component
function Form() {
  return (
    <div>
      <form>{/* form fields */}</form>
      <SubmitFormTool />
    </div>
  );
}

API Reference#

Parameters#

<ParametersTable
type="AssistantToolProps<TArgs, TResult>"
parameters={[
{
name: "toolName",
type: "string",
description: "The unique identifier for the tool",
required: true,
},
{
name: "parameters",
type: "StandardSchemaV1 | JSONSchema7",
description:
"Schema defining the tool's parameters (typically a Zod schema)",
required: true,
},
{
name: "execute",
type: "(args: TArgs, context: ToolExecutionContext) => TResult | Promise",
description:
"Function that implements the tool's behavior (required for frontend tools)",
required: true,
},
{
name: "description",
type: "string",
description: "Optional description of the tool's purpose",
},
{
name: "render",
type: "ComponentType<ToolCallMessagePartProps<TArgs, TResult>>",
description:
"Optional custom UI component for rendering the tool execution. Receives the following props:",
children: [
{
type: "ToolCallMessagePartProps<TArgs, TResult>",
parameters: [
{
name: "type",
type: '"tool-call"',
description: "The message part type",
},
{
name: "toolCallId",
type: "string",
description: "Unique identifier for this tool call",
},
{
name: "toolName",
type: "string",
description: "The name of the tool being called",
},
{
name: "args",
type: "TArgs",
description: "The arguments passed to the tool",
},
{
name: "argsText",
type: "string",
description: "String representation of the arguments",
},
{
name: "result",
type: "TResult | undefined",
description: "The result of the tool execution (if complete)",
},
{
name: "isError",
type: "boolean | undefined",
description: "Whether the result is an error",
},
{
name: "status",
type: "ToolCallMessagePartStatus",
description:
'The execution status object with a type property: "running", "complete", "incomplete", or "requires-action"',
},
{
name: "addResult",
type: "(result: TResult | ToolResponse) => void",
description:
"Function to add a result (useful for human-in-the-loop tools)",
},
{
name: "artifact",
type: "unknown",
description:
"Optional artifact data associated with the tool call",
},
],
},
],
},
]}
/>

Returns#

Returns a React component that:

• Provides the tool to the assistant when mounted
• Automatically removes the tool when unmounted
• Renders nothing in the DOM (returns null)

Example with Multiple Tools#

import { makeAssistantTool, tool } from "@assistant-ui/react";
import { z } from "zod";

// Define tools
const validateEmail = tool({
  parameters: z.object({
    email: z.string(),
  }),
  execute: ({ email }) => {
    const isValid = email.includes("@");
    return { isValid, reason: isValid ? "Valid email" : "Missing @" };
  },
});

const sendEmail = tool({
  parameters: z.object({
    to: z.string().email(),
    subject: z.string(),
    body: z.string(),
  }),
  execute: async (params) => {
    // Tool logic
    return { sent: true };
  },
});

// Create tool components
const EmailValidator = makeAssistantTool({
  ...validateEmail,
  toolName: "validateEmail",
});
const EmailSender = makeAssistantTool({
  ...sendEmail,
  toolName: "sendEmail",
});

// Use together
function EmailForm() {
  return (
    <div>
      <form>{/* form fields */}</form>
      <EmailValidator />
      <EmailSender />
    </div>
  );
}

Best Practices#

1. Parameter Validation

   • Always use Zod schemas to define parameters
   • Be specific about parameter types and constraints
   • Add helpful error messages to schema validations

2. Error Handling

   • Return meaningful error messages
   • Consider returning partial results when possible
   • Handle async errors appropriately

3. Composition

   • Break complex tools into smaller, focused ones
   • Consider tool dependencies and interactions
   • Use multiple tools together for complex functionality