# Tool Loadout

> Before the main agent loop, classify the request and hand the agent only the relevant subset of tools — not the whole 50+ tool catalog.

- **Category**: Agentic AI
- **Subcategory**: Tool Use & Environment
- **Canonical URL**: https://designpattern.fyi/patterns/tool_loadout/

---

## Description
**Intent**: Keep function-calling accuracy high even as the tool catalog grows large.

**Context**: Your agent has access to a large tool registry — MCP catalog, plugin marketplace, or internal directory with 50+ tools. Only a handful are relevant to any given request, and you can build a cheap classifier that runs ahead of the main loop.

**Solution**: Before the main loop, classify the request and select N relevant tools (rule-based routing by lane, or a quick model-based classifier). Expose only the selected subset to the main inference call. Tools outside the subset are unavailable for this request.


## Use Cases
- The tool registry is large and exposing all tools degrades selection accuracy.
- A classifier or rule can cheaply pick the relevant subset per request.
- Function-calling accuracy is a release-gate metric.





## Trade-offs


### Advantages

- Function-calling accuracy holds up at scale — fewer choices, better picks.

- Token budget for tool definitions stays manageable.




### Considerations & Drawbacks

- Filter mistakes hide capabilities the agent could have used.

- Filtering adds latency to every request.







---
**Reference**: [Original Source](https://www.agentpatternscatalog.org/patterns/tool-loadout/)