Tool Selection at Scale: Forty Tools, One Context

What changes when an agent has forty tools instead of six: choosing a loadout every turn, retrieval-based tool selection and its silent failure mode, namespacing across a dozen MCP servers, reading mis-selection in a trace, and the point where you split the agent instead of filtering the list.

Content current as of 2026-09.

Lessons

1. The loadout is a decision you make every turn
2. Retrieving tools the way you retrieve documents
3. Twelve servers, one flat list
4. Reading mis-selection in a trace
5. Filter the list, or split the agent