Verified65% confidenceTradeoffExact time
The quality of the description directly affects the accuracy of tool invocation; vague or ambiguous descriptions may cause the model to trigger a tool incorrectly or fail to call it when it should.
3
Sources
65%
Confidence
Long-term
Relevance
9/20/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedCandidate-set drift (especially the addition of distractor tools) caused most of the performance loss, whereas merely modifying tool descriptions or parameter schemas was comparatively less harmful.75% similarUnverifiedFor models that do not support tool calling, it is generally necessary to simulate tool-calling behavior through carefully designed prompts, though stability and accuracy will decline noticeably.73% similarUnverifiedCoarse-grained error type classification relies more on semantic understanding, while fine-grained error span localization relies more on boundary judgment and position awareness, and the model's strengths and weaknesses on these two types of tasks are very likely not consistent.73% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/936644API
curl https://kongchang.com/api/v1/knowledge/claims/936644MCP
get_claim(id=936644)