Tool Transition Fusion
Mine your tool-call telemetry for high-probability X→Y transitions and fuse those pairs into single composite tools — one fewer step per fused pair.
Intent & Description
🎯 Intent
Use production data to identify and eliminate redundant sequential tool calls.
📋 Context
Your agent has accumulated tool-call telemetry showing which tool consistently follows which other tool. Each tool call is a decoding decision that can fail, costs tokens, and adds latency. Some X→Y transitions happen 80%+ of the time.
💡 Solution
Sweep telemetry for transitions P(Y|X) above a threshold (e.g., 0.8). Wrap qualifying X→Y pairs in a composite tool whose signature is X’s input and Y’s output. Add the composite to the catalog; keep X and Y available for edge cases. Re-run the sweep periodically as task mix shifts. Document why each composite exists so reviewers know it was data-driven, not author intuition.
Real-world Use Case
- Sufficient tool-call telemetry exists to estimate transition probabilities.
- Per-step latency or decoding-error rate is a measurable cost driver.
- A clear majority transition (>0.8 conditional probability) recurs across many sessions.
Source
📌 TL;DR
If X is always followed by Y in your telemetry, fuse them into one tool. One fewer decoding step, one fewer failure mode. Re-sweep periodically as usage shifts.
Advantages
- Cuts one step and one decoding decision per fused pair.
- Removes a recurring failure mode where the model picks the wrong follow-up.
- Telemetry-driven fusion keeps the catalog grounded in reality, not author intuition.
Disadvantages
- Composite tools hide the X/Y boundary from anyone reading a trace.
- Over-fusion entrenches the dominant path and makes divergence slower when task mix shifts.
- Threshold choice is a judgment call — too low fuses noise, too high yields nothing.