# init(allPass:percentagePass:argumentMatchModel:) Creates a new tool-call expectations evaluator with a custom language model for semantic matching of natural language argument matchers. ``` init(allPass: Metric, percentagePass: Metric, argumentMatchModel: any LanguageModel) ``` ## Parameters `allPass` The metric for the strict pass or fail result. `percentagePass` The metric for the partial score result. `argumentMatchModel` The language model to use for semantic matching. ## Discussion ```swift let allPassMetric = Metric("Tools All Pass") let percentagePassMetric = Metric("Tools Percentage Pass") let evaluator = ToolCallEvaluator>( allPass: allPassMetric, percentagePass: percentagePassMetric, argumentMatchModel: SystemLanguageModel.default ) ``` --- Copyright © 2026 Apple Inc. All rights reserved. | [Terms of Use](https://www.apple.com/legal/internet-services/terms/site.html) | [Privacy Policy](https://www.apple.com/privacy/privacy-policy)