Inference Logoinference.sh

Adding Tools

Tools extend what your agent can do. There are five types of tools.


Tool Types

TypeWhat it isUse case
AppAny app from the gridImage generation, search, transcription
AgentAnother agentDelegate specialized tasks
HookExternal webhookConnect to your own services
ClientCode-executed toolsBrowser automation, custom logic
InternalBuilt-in agent capabilitiesMemory, planning, widgets

All tools are managed in one place: the Tools tab.


Adding an App Tool

  1. Open your agent's settings
  2. Go to the Tools tab
  3. Click Add ToolApp Tool
  4. Search and select an app

The agent can now call this app.

What happens automatically:

  • Name is extracted from the app
  • Input schema becomes tool parameters
  • You can customize the description shown to the agent

Configuring Setup & Default Inputs

App tools support two types of pre-configuration:

SettingPurposeWhen it's used
SetupOne-time configuration valuesPassed to the app on every call (e.g., API keys, model selection)
Default InputsDefault parameter valuesMerged with agent's call — agent can override these

To configure:

  1. After adding an app tool, click Configure Setup or Configure Default Inputs
  2. Fill in the form fields
  3. Save the agent

Example: An image generation tool might have:

  • Setup: API key, default model, safety settings
  • Default Inputs: Default resolution, style preset

The agent only sees input parameters — setup values are hidden from the LLM.


Adding an Agent Tool

Agents can delegate to other agents:

  1. Go to Tools tab
  2. Click Add ToolAgent Tool
  3. Select another agent

The main agent can now delegate tasks to it.

code
1Main Agent2 Research Agent (gathers information)3 Writing Agent (creates content)4 Editor Agent (reviews and polishes)

See Sub-Agents for more details.


Adding a Webhook Tool

Connect your agent to external services:

  1. Go to Tools tab
  2. Click Add ToolWebhook Tool
  3. Enter a name and webhook URL
  4. Optionally add a secret and input schema

When called, the hook receives:

  • Tool arguments
  • A callback URL to return results

See Webhooks for implementation details.


Client Tools

Client tools execute in your application code. They're defined with a handler function that runs when the agent calls the tool.

typescript
1import { tool, string } from '@inferencesh/sdk'23const myTool = tool('search_ui')4  .describe('Scans the UI for interactive elements')5  .param('query', string('Search query'))6  .handler(async (args) => {7    // Your code runs here8    return JSON.stringify({ results: [...] })9  })

Client tools are useful for:

  • Browser automation (DOM interaction)
  • Accessing local resources
  • Custom business logic
  • Integrating with frontend frameworks

Internal Tools

Internal tools are built-in capabilities provided by the runtime. They're automatically available based on agent configuration.

Plan Tools

Task planning for complex multi-step operations:

ToolDescription
plan_createCreate a plan with steps
plan_updateUpdate step status
plan_loadView current plan

Memory Tools

Key-value storage that persists across messages:

ToolDescription
memory_setStore a value
memory_getRetrieve a value
memory_getallGet all stored memories

Widget Tool

UI rendering for interactive forms (top-level agents only):

ToolDescription
widgetCreate forms, buttons, cards

Finish Tool

For agents to report structured output:

ToolDescription
finishReport status and results

When output_schema is set on the agent config, the finish tool validates results against the schema. See Structured Output for details.

Skills Tool

Load skill content on-demand (when agent has skills defined):

ToolDescription
skill_getRetrieve a skill's full content

See Skills for more details on defining and using skills.


Example App Tools

ToolWhat it does
stable-diffusionGenerate images
whisperTranscribe audio
summarizeCondense text
web-searchSearch the internet

How Agents Use Tools

When you chat:

code
1You: Generate a sunset image23Agent: I'll create that for you.4       [Calling stable-diffusion with prompt "sunset"]56       Here's your sunset image!

The agent decides when to use which tool based on your request.


Tool Descriptions

Each tool has a description that tells the agent what it does. Good descriptions help the agent choose the right tool:

Generic:

code
1Search the web

Better:

code
1Search the web for current information. Use when you need up-to-date2facts, news, or information not in your training data.

Next

Sub-Agents

we use cookies

we use cookies to ensure you get the best experience on our website. for more information on how we use cookies, please see our cookie policy.

by clicking "accept", you agree to our use of cookies.
learn more.