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.
Intent & 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.
Real-world Use Case
- 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.
Source
📌 TL;DR
Classify the request, pick the relevant tools, hand only those to the agent. Selection accuracy stays high even with hundreds of tools in the catalog.
Advantages
- Function-calling accuracy holds up at scale — fewer choices, better picks.
- Token budget for tool definitions stays manageable.
Disadvantages
- Filter mistakes hide capabilities the agent could have used.
- Filtering adds latency to every request.