Create Client Tool

by cognitedata7758093d8656No license6 starsListed Oct 8, 2026Updated Oct 8, 2026Repository updated 2 days ago

Scaffolds an AtlasTool for an already-approved in-app useAtlasChat UI. For EOS sidebar tools, use integrate-fusion-agent (createAgentAction) instead. Triggers: AtlasTool, useAtlasChat tool, in-app atlas client tool.

AI-generated overview

Scaffolds an AtlasTool client tool for an approved in-app useAtlasChat integration, with TypeBox schemas and wiring.

What it does
Guides the agent through creating a browser-side AtlasTool for an app that already has an approved in-app useAtlasChat integration. It covers reading the codebase, defining the tool with a TypeBox parameter schema and an execute function returning output and details, registering the tool in the useAtlasChat tools array, and optionally rendering structured tool results from message.toolCalls. It produces instructions and code snippets rather than running anything.
When to use it
Use when adding a client-side tool that the Atlas Agent can invoke in an app with an existing approved useAtlasChat integration. For EOS sidebar tools, the document says to use integrate-fusion-agent with createAgentAction instead.
Requirements
Requires a vendored src/atlas-agent/ directory and the @sinclair/typebox package from integrate-atlas-chat, plus an app with an approved in-app useAtlasChat integration. It ships no scripts and only uses Read, Glob, Grep, Edit and Write.

Create a Client Tool

Scaffold an AtlasTool named $ARGUMENTS. If the app has no approved in-app useAtlasChat, implement a Fusion action via integrate-fusion-agent instead.

Prerequisite: vendored src/atlas-agent/ and @sinclair/typebox from integrate-atlas-chat.

Background

Client tools let the Atlas Agent invoke browser-side logic — charts, local state, UI panels, navigation. The agent decides when to call; the app executes and returns a result.

  1. Agent responds with a clientTool action
  2. TypeBox validates the arguments
  3. execute() runs in the browser and returns { output, details }
  4. output (string) is sent back to the agent
  5. details is available on message.toolCalls for the UI to render

Step 1 — Understand the codebase

Before writing anything, read:

  • The file where useAtlasChat is called (often src/App.tsx or a chat hook) to find where tools is passed — imports are typically from ./atlas-agent/react after integrate-atlas-chat
  • Any existing tool definitions to match the file/naming conventions

Step 2 — Define the tool

Use Type from @sinclair/typebox for the parameters schema (compile-time types + runtime validation).

ts
import { Type } from "@sinclair/typebox";import type { AtlasTool } from "./atlas-agent/types";
export const myTool: AtlasTool = {  name: "my_tool",            // snake_case — this is what the agent uses to invoke it  description:    "One sentence describing what this tool does and when the agent should call it.",  parameters: Type.Object({    exampleParam: Type.String({ description: "What this param is for" }),    optionalNum: Type.Optional(Type.Number({ description: "..." })),  }),  execute: async (args) => {    return {      output: "Plain text summary sent back to the agent",      details: {        // Any structured data you want available in the UI via message.toolCalls      },    };  },};

Adjust the ./atlas-agent/... path if the tool file is not directly under src/ next to the atlas-agent folder (for example ../atlas-agent/types from src/tools/).

TypeBox quick reference

SchemaUsage
Type.String()string
Type.Number()number
Type.Boolean()boolean
Type.Literal("foo")exact value
Type.Union([Type.Literal("a"), Type.Literal("b")])enum
Type.Array(Type.String())string[]
Type.Object({ ... })object
Type.Optional(...)mark any field optional

Always add a description on the tool and on each parameter — the agent uses those strings.


Step 3 — Wire into useAtlasChat

Find the useAtlasChat call and add the tool to the tools array:

ts
const { messages, send, ... } = useAtlasChat({  client: isLoading ? null : sdk,  agentExternalId: AGENT_EXTERNAL_ID,  tools: [myTool],   // add here});

Step 4 — Render tool results (if needed)

If the tool returns structured details, render them in the message list. message.toolCalls is a ToolCall[] — one entry per tool call (client-side and server-side) in call order.

tsx
{msg.toolCalls?.map((tc, i) => (  // tc.name    — tool name  // tc.output  — the string sent back to the agent  // tc.details — your structured data (cast to your known shape)  <MyToolOutput key={i} data={tc.details as MyToolDetails} />))}

Source and attribution

Source:cognitedata/builder-skillsinskills/create-client-toolat commit7758093

License: No license

Content belongs to its original authors. SourceWeft indexes it from a public repository.

Report or request removal

Create Client Tool Agent Skill | SourceWeft