Defined in: activities/chat/tools/tool-definition.ts:107

Tool definition builder that allows creating server or client tools from a shared definition

• ToolDefinitionInstance<TInput, TOutput, TName>

TInput extends SchemaInput = SchemaInput

TOutput extends SchemaInput = SchemaInput

TName extends string = string

__toolSide: "definition";

Defined in: activities/chat/tools/tool-definition.ts:50

ToolDefinitionInstance.__toolSide

client: (execute?) => ClientTool<TInput, TOutput, TName>;

Defined in: activities/chat/tools/tool-definition.ts:125

Create a client-side tool with optional execute function

(args) => | InferSchemaType<TOutput> | Promise<InferSchemaType<TOutput>>

ClientTool<TInput, TOutput, TName>

description: string;

Defined in: types.ts:413

Clear description of what the tool does.

This is crucial - the model uses this to decide when to call the tool. Be specific about what the tool does, what parameters it needs, and what it returns.

"Get the current weather in a given location. Returns temperature, conditions, and forecast."

ToolDefinitionInstance.description

optional execute: (args, context?) => any;

Defined in: types.ts:493

Optional function to execute when the model calls this tool.

If provided, the SDK will automatically execute the function with the model's arguments and feed the result back to the model. This enables autonomous tool use loops.

Can return any value - will be automatically stringified if needed.

any

The arguments parsed from the model's tool call (validated against inputSchema)

ToolExecutionContext

any

Result to send back to the model (validated against outputSchema if provided)

execute: async (args) => {
  const weather = await fetchWeather(args.location);
  return weather; // Can return object or string
}

ToolDefinitionInstance.execute

optional inputSchema: TInput;

Defined in: types.ts:453

Schema describing the tool's input parameters.

Can be any Standard JSON Schema compliant schema (Zod, ArkType, Valibot, etc.) or a plain JSON Schema object. Defines the structure and types of arguments the tool accepts. The model will generate arguments matching this schema. Standard JSON Schema compliant schemas are converted to JSON Schema for LLM providers.

• https://standardschema.dev/json-schema
• https://json-schema.org/

// Using Zod v4+ schema (natively supports Standard JSON Schema)
import { z } from 'zod';
z.object({
  location: z.string().describe("City name or coordinates"),
  unit: z.enum(["celsius", "fahrenheit"]).optional()
})

// Using ArkType (natively supports Standard JSON Schema)
import { type } from 'arktype';
type({
  location: 'string',
  unit: "'celsius' | 'fahrenheit'"
})

// Using plain JSON Schema
{
  type: 'object',
  properties: {
    location: { type: 'string', description: 'City name or coordinates' },
    unit: { type: 'string', enum: ['celsius', 'fahrenheit'] }
  },
  required: ['location']
}

ToolDefinitionInstance.inputSchema

optional lazy: boolean;

Defined in: types.ts:499

If true, this tool is lazy and will only be sent to the LLM after being discovered via the lazy tool discovery mechanism. Only meaningful when used with chat().

ToolDefinitionInstance.lazy

optional metadata: Record<string, any>;

Defined in: types.ts:502

Additional metadata for adapters or custom extensions

ToolDefinitionInstance.metadata

name: TName;

Defined in: types.ts:403

Unique name of the tool (used by the model to call it).

Should be descriptive and follow naming conventions (e.g., snake_case or camelCase). Must be unique within the tools array.

"get_weather", "search_database", "sendEmail"

ToolDefinitionInstance.name

optional needsApproval: boolean;

Defined in: types.ts:496

If true, tool execution requires user approval before running. Works with both server and client tools.

ToolDefinitionInstance.needsApproval

optional outputSchema: TOutput;

Defined in: types.ts:474

Optional schema for validating tool output.

Can be any Standard JSON Schema compliant schema or a plain JSON Schema object. If provided with a Standard Schema compliant schema, tool results will be validated against this schema before being sent back to the model. This catches bugs in tool implementations and ensures consistent output formatting.

Note: This is client-side validation only - not sent to LLM providers. Note: Plain JSON Schema output validation is not performed at runtime.

// Using Zod
z.object({
  temperature: z.number(),
  conditions: z.string(),
  forecast: z.array(z.string()).optional()
})

ToolDefinitionInstance.outputSchema

server: (execute) => ServerTool<TInput, TOutput, TName>;

Defined in: activities/chat/tools/tool-definition.ts:115

Create a server-side tool with execute function

(args, context?) => | InferSchemaType<TOutput> | Promise<InferSchemaType<TOutput>>

ServerTool<TInput, TOutput, TName>