Unverified50% confidenceBenchmarkExact time
Appending 1-5 real invocation examples to tool descriptions can raise tool-calling accuracy on certain benchmarks from about 72% to 90%.
1
Sources
50%
Confidence
Long-term
Relevance
10/16/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedTools scoring below 40 were correctly selected 95.5% of the time, while tools scoring 60 to 79 instead reached 100%.79% similarUnverifiedAfter rewriting tool definitions according to the three-element principle and similar guidelines, the model's invocation accuracy improved from less than half to over 80%.77% similarUnverifiedEvidence-driven pre-improvement validation improved precision from 58.6% to 72.3%, and reduced unsupported objectives per round from 1.93 to 0.50.70% similarUnverifiedProviding specific input and expected output examples in the prompt can improve docstring generation quality from approximately 30% usable to approximately 85% usable.70% similarUnverifiedWhen recombining rules seen during training, symbolic descriptions match or even exceed the example approach, reaching 99% versus 95% accuracy on new combinations.70% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1047262API
curl https://kongchang.com/api/v1/knowledge/claims/1047262MCP
get_claim(id=1047262)