Tool Call Rendering
Render your agent's tool calls with custom UI components.
"""Agent backing the `tool-rendering` demo.Custom per-tool renderers (WeatherCard, FlightListCard, StockCard,D20Card) plus a wildcard catch-all on the frontend. Backend tools areidentical across the basic tool-rendering variants — seetool_rendering_common.py."""from __future__ import annotationsfrom google.adk.agents import LlmAgentfrom agents.shared_chat import get_model, stop_on_terminal_textfrom agents.tool_rendering_common import ( TOOL_RENDERING_INSTRUCTION, get_stock_price, get_weather, roll_d20, search_flights,)tool_rendering_agent = LlmAgent( name="ToolRenderingAgent", model=get_model(), instruction=TOOL_RENDERING_INSTRUCTION, tools=[get_weather, search_flights, get_stock_price, roll_d20], after_model_callback=stop_on_terminal_text,)What is this?#
Tools are how an LLM invokes predefined, typically-deterministic functions. Tool rendering lets you decide how each of those tool calls appears in the chat. Instead of showing raw JSON, you register a React component that draws a branded card for the call (arguments, live status, and the eventual result). This is the Generative UI variant CopilotKit calls tool rendering.
Free course: See this pattern built end-to-end in Build Interactive Agents with Generative UI — a free DeepLearning.AI short course taught by CopilotKit's CEO covering the full Generative UI spectrum (Controlled, Declarative, and Open-Ended).
When should I use this?#
Render tool calls when you want to:
- Show users exactly what tools the agent is invoking and with what arguments
- Display live progress indicators while a tool executes
- Render rich, polished results once a tool completes
- Give tool-heavy agents a transparent, on-brand chat experience
Default tool rendering (zero-config)#
The simplest entry point: call useDefaultRenderTool() with no arguments.
CopilotKit registers its built-in DefaultToolCallRenderer as the *
wildcard: every tool call renders as a tidy status card (tool name, live
Running → Done pill, collapsible arguments/result) without you writing
any UI.
Without this hook the runtime has no * renderer and tool calls are
invisible; the user only sees the assistant's final text summary.
// Opt in to CopilotKit's built-in default tool-call card. Called with // no config so the package-provided `DefaultToolCallRenderer` is used // as the wildcard renderer — this is the "out-of-the-box" UI the cell // is meant to showcase. useDefaultRenderTool();Here's what the built-in status card looks like for each tool call:
"use client";// Tool Rendering — DEFAULT CATCH-ALL variant (simplest).//// This cell is the simplest point in the three-way progression. The// backend exposes a handful of mock tools (get_weather, search_flights,// get_stock_price, roll_dice) and the frontend ONLY opts into// CopilotKit's built-in default tool-call card — no per-tool renderers,// no custom wildcard UI.//// `useDefaultRenderTool()` (called with no config) registers the built-// in `DefaultToolCallRenderer` under the `*` wildcard. That renderer// shows the tool name, a live status pill (Running → Done), and a// collapsible "Arguments / Result" section that fills in as the call// progresses. Without this hook the runtime has NO `*` renderer, so// `useRenderToolCall` falls through to `null` and tool calls are// invisible — the user only sees the assistant's final text summary.import React from "react";import { CopilotKit, CopilotChat, useConfigureSuggestions, useDefaultRenderTool,} from "@copilotkit/react-core/v2";export default function ToolRenderingDefaultCatchallDemo() { return ( <CopilotKit runtimeUrl="/api/copilotkit" agent="tool-rendering-default-catchall" > <div className="flex justify-center items-center h-screen w-full"> <div className="h-full w-full max-w-4xl"> <Chat /> </div> </div> </CopilotKit> );}function Chat() { // Opt in to CopilotKit's built-in default tool-call card. Called with // no config so the package-provided `DefaultToolCallRenderer` is used // as the wildcard renderer — this is the "out-of-the-box" UI the cell // is meant to showcase. useDefaultRenderTool(); useConfigureSuggestions({ suggestions: [ { title: "Weather in SF", message: "What's the weather in San Francisco?", }, { title: "Find flights", message: "Find flights from SFO to JFK.", }, { title: "Roll a d20", message: "Roll a 20-sided die.", }, ], available: "always", }); return ( <CopilotChat agentId="tool-rendering-default-catchall" className="h-full rounded-2xl" /> );}Custom catch-all#
Once you want on-brand chrome, pass a render function to
useDefaultRenderTool. It's a convenience wrapper around
useRenderTool({ name: "*", ... }): one wildcard renderer handles every
tool call, named or not:
// `useDefaultRenderTool` is a convenience wrapper around // `useRenderTool({ name: "*", ... })` — a single wildcard renderer // that handles every tool call not claimed by a named renderer. useDefaultRenderTool( { render: ({ name, parameters, status, result }) => ( <CustomCatchallRenderer name={name} parameters={parameters} status={status as CatchallToolStatus} result={result} /> ), }, [], );Here's the branded catch-all in action, where every tool call gets the same on-brand card:
"use client";// Tool Rendering — CUSTOM CATCH-ALL variant (middle of the progression).//// Same backend tools as `tool-rendering-default-catchall`, but this// cell opts out of CopilotKit's built-in default tool-call UI by// registering a SINGLE custom wildcard renderer via// `useDefaultRenderTool`. The same branded card now paints every tool// call — no per-tool renderers yet.import React from "react";import { CopilotKit, CopilotChat, useDefaultRenderTool,} from "@copilotkit/react-core/v2";import { CustomCatchallRenderer, type CatchallToolStatus,} from "./custom-catchall-renderer";import { useSuggestions } from "./suggestions";export default function ToolRenderingCustomCatchallDemo() { return ( <CopilotKit runtimeUrl="/api/copilotkit" agent="tool-rendering-custom-catchall" > <div className="flex justify-center items-center h-screen w-full"> <div className="h-full w-full max-w-4xl"> <Chat /> </div> </div> </CopilotKit> );}function Chat() { // `useDefaultRenderTool` is a convenience wrapper around // `useRenderTool({ name: "*", ... })` — a single wildcard renderer // that handles every tool call not claimed by a named renderer. useDefaultRenderTool( { render: ({ name, parameters, status, result }) => ( <CustomCatchallRenderer name={name} parameters={parameters} status={status as CatchallToolStatus} result={result} /> ), }, [], ); useSuggestions(); return ( <CopilotChat agentId="tool-rendering-custom-catchall" className="h-full rounded-2xl" /> );}Per-tool renderers#
The most expressive path is one renderer per tool name. The primary
tool-rendering cell wires two: get_weather draws a branded
WeatherCard, search_flights draws a FlightListCard. Each renderer
receives the tool's parsed arguments, a live status, and (once the agent
returns) the result:
import React from "react";import { CopilotKit, CopilotChat, useRenderTool, useDefaultRenderTool,} from "@copilotkit/react-core/v2";import { z } from "zod";import { WeatherCard } from "./weather-card";import { FlightListCard, type Flight } from "./flight-list-card";import { StockCard } from "./stock-card";import { D20Card } from "./d20-card";import { CustomCatchallRenderer, type CatchallToolStatus,} from "./custom-catchall-renderer";import { parseJsonResult } from "../_shared/parse-json-result";import { useSuggestions } from "./suggestions";interface WeatherResult { city?: string; temperature?: number; humidity?: number; wind_speed?: number; conditions?: string;}interface FlightSearchResult { origin?: string; destination?: string; flights?: Flight[];}interface StockResult { ticker?: string; price_usd?: number; change_pct?: number;}interface D20Result { value?: number; result?: number; sides?: number;}export default function ToolRenderingDemo() { return ( <CopilotKit runtimeUrl="/api/copilotkit" agent="tool-rendering"> <div className="flex justify-center items-center h-screen w-full"> <div className="h-full w-full max-w-4xl"> <Chat /> </div> </div> </CopilotKit> );}function Chat() { // Per-tool renderer #1: get_weather → branded WeatherCard. useRenderTool( { name: "get_weather", parameters: z.object({ location: z.string(), }), render: ({ parameters, result, status }) => { const loading = status !== "complete"; const parsed = parseJsonResult<WeatherResult>(result); return ( <WeatherCard loading={loading} location={parameters?.location ?? parsed.city ?? ""} temperature={parsed.temperature} humidity={parsed.humidity} windSpeed={parsed.wind_speed} conditions={parsed.conditions} /> ); }, }, [], );The flight renderer follows the same pattern with a different component and schema:
import React from "react";import { CopilotKit, CopilotChat, useRenderTool, useDefaultRenderTool,} from "@copilotkit/react-core/v2";import { z } from "zod";import { WeatherCard } from "./weather-card";import { FlightListCard, type Flight } from "./flight-list-card";import { StockCard } from "./stock-card";import { D20Card } from "./d20-card";import { CustomCatchallRenderer, type CatchallToolStatus,} from "./custom-catchall-renderer";import { parseJsonResult } from "../_shared/parse-json-result";import { useSuggestions } from "./suggestions";interface WeatherResult { city?: string; temperature?: number; humidity?: number; wind_speed?: number; conditions?: string;}interface FlightSearchResult { origin?: string; destination?: string; flights?: Flight[];}interface StockResult { ticker?: string; price_usd?: number; change_pct?: number;}interface D20Result { value?: number; result?: number; sides?: number;}export default function ToolRenderingDemo() { return ( <CopilotKit runtimeUrl="/api/copilotkit" agent="tool-rendering"> <div className="flex justify-center items-center h-screen w-full"> <div className="h-full w-full max-w-4xl"> <Chat /> </div> </div> </CopilotKit> );}function Chat() { // Per-tool renderer #1: get_weather → branded WeatherCard. useRenderTool( { name: "get_weather", parameters: z.object({ location: z.string(), }), render: ({ parameters, result, status }) => { const loading = status !== "complete"; const parsed = parseJsonResult<WeatherResult>(result); return ( <WeatherCard loading={loading} location={parameters?.location ?? parsed.city ?? ""} temperature={parsed.temperature} humidity={parsed.humidity} windSpeed={parsed.wind_speed} conditions={parsed.conditions} /> ); }, }, [], ); // Per-tool renderer #2: search_flights → branded FlightListCard. useRenderTool( { name: "search_flights", parameters: z.object({ origin: z.string(), destination: z.string(), }), render: ({ parameters, result, status }) => { const loading = status !== "complete"; const parsed = parseJsonResult<FlightSearchResult>(result); return ( <FlightListCard loading={loading} origin={parameters?.origin ?? parsed.origin ?? ""} destination={parameters?.destination ?? parsed.destination ?? ""} flights={parsed.flights ?? []} /> ); }, }, [], );The name you pass to useRenderTool must match the tool name the agent
exposes; that's how the runtime routes the call to your component.
Per-tool renderers compose with a catch-all: named renderers claim the
"interesting" tools and a wildcard handles everything else. In the primary
cell, the same CustomCatchallRenderer from above catches get_stock_price
and roll_dice:
// Wildcard catch-all for anything that doesn't match a per-tool // renderer above. useDefaultRenderTool( { render: ({ name, parameters, status, result }) => ( <CustomCatchallRenderer name={name} parameters={parameters} status={status as CatchallToolStatus} result={result} /> ), }, [], );The backend tool definition#
The frontend renderer only sees what the agent sends down. Here's the
matching Python definition for get_weather, a standard LangChain tool,
no CopilotKit-specific plumbing required:
from __future__ import annotationsfrom random import choice, randintfrom google.adk.tools import ToolContextdef get_weather(tool_context: ToolContext, location: str) -> dict: """Get the current weather for a given location.""" return { "city": location, "temperature": 68, "humidity": 55, "wind_speed": 10, "conditions": "Sunny", }