> ## Documentation Index
> Fetch the complete documentation index at: https://noorle.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Tool Exposure

> Control how tools are presented to agents and MCP clients.

**Tool Exposure** controls how your agent's or gateway's tools are presented to the consuming AI. As you attach more capabilities, the number of available tools grows — Tool Exposure lets you manage that complexity.

## Configuration

<Steps>
  <Step title="Open Settings">
    **Agents** > Select agent > **Settings** (or **Gateways** > Select gateway > **Settings**)
  </Step>

  <Step title="Find Tool Exposure">
    Locate the **Tool Exposure** section
  </Step>

  <Step title="Choose a Mode">
    Select **Smart** (recommended), **Omni**, or **Individual**
  </Step>

  <Step title="Save">
    Click **Save**
  </Step>
</Steps>

## Visibility Modes

| Mode                             | Tools Exposed                          | Best For                               |
| -------------------------------- | -------------------------------------- | -------------------------------------- |
| **Smart** (default, recommended) | 3 meta-tools for progressive discovery | Balanced control and flexibility       |
| **Omni**                         | Single `omni_tool`                     | Simplest interface, maximum automation |
| **Individual**                   | All tools directly                     | Full control, power users              |

## How Each Mode Works

### Smart Mode (Recommended)

Exposes 3 meta-tools for progressive discovery:

1. **discover\_tools** — List available tools matching a task description
2. **get\_tool\_schema** — Get detailed schema for a specific tool
3. **execute\_tool** — Run a tool with specified parameters

The AI first discovers what's available, inspects the right tool, then executes it. This gives the AI context to make good choices without overwhelming it with every tool upfront.

### Omni Mode

Exposes a single `omni_tool`. The AI describes what it wants in natural language, and an LLM-powered discovery layer finds and executes the right tool automatically.

```
Tools available: omni_tool

Request: "Search for Python tutorials"
→ Omni Tool discovers web_search
→ Extracts parameters automatically
→ Executes and returns result with metadata
```

### Individual Mode

Exposes every tool directly. The AI sees the full list and picks which to call. Best when you have a small, well-defined set of tools or need precise control.

## Confidence Scoring (Omni Mode)

In Omni mode, the discovery LLM rates match confidence (0.0–1.0):

* **0.95+** — Very confident (clear match)
* **0.80–0.95** — High confidence (strong match)
* **0.70–0.80** — Moderate (passes default threshold)
* **Below 0.70** — Rejected, asks for clarification

The confidence threshold is a global setting (default: 0.7). Below the threshold, Omni Tool asks the user to clarify instead of guessing wrong.

## Which Mode to Choose

| Scenario                                  | Recommended Mode            |
| ----------------------------------------- | --------------------------- |
| General-purpose agent with many tools     | **Smart**                   |
| Simplest possible interface for end users | **Omni**                    |
| Small, well-defined tool set              | **Individual**              |
| Agent needs to adapt to varied requests   | **Smart** or **Omni**       |
| Maximum speed, minimal latency            | **Individual**              |
| MCP gateway for developer clients         | **Smart** or **Individual** |

## Applies to Both Agents and Gateways

Tool Exposure is configurable on both agents and MCP gateways. The behavior is the same — it controls how tools are presented to the consuming AI client.

## Cost

For current pricing details, see [Pricing](https://noorle.com/pricing/).

In Smart and Omni modes, tool discovery adds a small LLM call. You only pay for the actual tool execution.

## Troubleshooting

| Problem                         | Solution                                                     |
| ------------------------------- | ------------------------------------------------------------ |
| Omni picks wrong tool           | Make request more specific, or switch to Smart mode          |
| Discovery adds too much latency | Switch to Individual mode for speed-critical cases           |
| Agent not finding tools         | Check that capabilities are attached and tools are available |
| Low confidence scores           | Requests are ambiguous — add more detail                     |

## Next Steps

* [Tool Exposure Concepts](/docs/learn/concepts/omni-tool)
* [Creating Agents](/docs/run/agents/creating-an-agent)
* [Attaching Capabilities](/docs/run/agents/attaching-capabilities)
* [MCP Gateway Configuration](/docs/run/platform/mcp-gateway)