Unverified50% confidenceTradeoffExact time
When tool descriptions fill the context window, models are more prone to selecting the wrong tool among many similar ones.
1
Sources
50%
Confidence
Long-term
Relevance
10/8/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen multiple tools are semantically similar, the model's tool selection is essentially a multi-class classification problem, and the more candidate classes there are, the higher the misclassification rate.80% similarUnverifiedIf the data always provides tools that get used, the model learns the erroneous association that it must use a tool whenever it sees one.76% similarUnverifiedThe quality of tool descriptions directly affects the model's invocation accuracy; vague descriptions or ambiguous parameter naming will cause the model to frequently pass in incorrect parameters.71% similarUnverifiedIn multi-step tool-calling chains, errors can propagate and amplify between reasoning nodes, making root-cause analysis difficult.68% similarUnverifiedWhen the number of tools increases and tools with similar names and overlapping functions appear (such as get_x, fetch_x, read_x), the LLM's tool selection becomes unreliable.68% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/987561API
curl https://kongchang.com/api/v1/knowledge/claims/987561MCP
get_claim(id=987561)