Principle
Measure the active tool set, not the catalog size
The catalog is inventory. The working set is cognitive load.
When it fits
- A team argues about how many tools an agent can support but does not know how much tool context each request actually sees.
When to avoid it
- Do not optimize the working set in isolation. Extra routing steps or low recall can erase the savings.
Why it matters
Track the count and token footprint of tool schemas active per request, alongside tool-selection accuracy and task success. A large catalog can be acceptable if the working set remains relevant; a small catalog can still be wasteful if every verbose schema is always loaded.
An example
Two agents both expose 80 available tools. One routinely shows six relevant schemas; the other shows all 80. Catalog size alone hides the meaningful difference.
Check your result
Tool-context changes are evaluated with working-set size and task outcomes rather than only total tools registered.
Keep this limit in mind
- Do not optimize the working set in isolation. Extra routing steps or low recall can erase the savings.
Evidence and sources
The active number and size of tool schemas presented to the model can be measured separately from the total catalog to diagnose context and selection overhead.
A smaller working set is not automatically better; over-pruning can reduce task coverage or force extra routing turns.
The 100-Tool Agent Is a Trap: Scaling with Semantic Routers and JIT Context · 12:47-20:22, measure the working set and connect retrieval to evaluation and maintenance