Configuration
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:- discover_tools — List available tools matching a task description
- get_tool_schema — Get detailed schema for a specific tool
- execute_tool — Run a tool with specified parameters
Omni Mode
Exposes a singleomni_tool. The AI describes what it wants in natural language, and an LLM-powered discovery layer finds and executes the right tool automatically.
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
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. 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 |