@mastra/mcp-docs-server 1.1.7 → 1.1.8

package/.docs/reference/evals/answer-similarity.md

@@ -4,45 +4,43 @@ The `createAnswerSimilarityScorer()` function creates a scorer that evaluates ho
 
 ## Parameters
 
-**model:** (`LanguageModel`): The language model used to evaluate semantic similarity between outputs and ground truth.
+**model** (`LanguageModel`): The language model used to evaluate semantic similarity between outputs and ground truth.
 
-**options:** (`AnswerSimilarityOptions`): Configuration options for the scorer.
+**options** (`AnswerSimilarityOptions`): Configuration options for the scorer.
 
-### AnswerSimilarityOptions
+**options.requireGroundTruth** (`boolean`): Whether to require ground truth for evaluation. If false, missing ground truth returns score 0.
 
-**requireGroundTruth:** (`boolean`): Whether to require ground truth for evaluation. If false, missing ground truth returns score 0. (Default: `true`)
+**options.semanticThreshold** (`number`): Weight for semantic matches vs exact matches (0-1).
 
-**semanticThreshold:** (`number`): Weight for semantic matches vs exact matches (0-1). (Default: `0.8`)
+**options.exactMatchBonus** (`number`): Additional score bonus for exact matches (0-1).
 
-**exactMatchBonus:** (`number`): Additional score bonus for exact matches (0-1). (Default: `0.2`)
+**options.missingPenalty** (`number`): Penalty per missing key concept from ground truth.
 
-**missingPenalty:** (`number`): Penalty per missing key concept from ground truth. (Default: `0.15`)
+**options.contradictionPenalty** (`number`): Penalty for contradictory information. High value ensures wrong answers score near 0.
 
-**contradictionPenalty:** (`number`): Penalty for contradictory information. High value ensures wrong answers score near 0. (Default: `1.0`)
+**options.extraInfoPenalty** (`number`): Mild penalty for extra information not present in ground truth (capped at 0.2).
 
-**extraInfoPenalty:** (`number`): Mild penalty for extra information not present in ground truth (capped at 0.2). (Default: `0.05`)
-
-**scale:** (`number`): Score scaling factor. (Default: `1`)
+**options.scale** (`number`): Score scaling factor.
 
 This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but **requires ground truth** to be provided in the run object.
 
 ## .run() Returns
 
-**runId:** (`string`): The id of the run (optional).
+**runId** (`string`): The id of the run (optional).
 
-**score:** (`number`): Similarity score between 0-1 (or 0-scale if custom scale used). Higher scores indicate better similarity to ground truth.
+**score** (`number`): Similarity score between 0-1 (or 0-scale if custom scale used). Higher scores indicate better similarity to ground truth.
 
-**reason:** (`string`): Human-readable explanation of the score with actionable feedback.
+**reason** (`string`): Human-readable explanation of the score with actionable feedback.
 
-**preprocessStepResult:** (`object`): Extracted semantic units from output and ground truth.
+**preprocessStepResult** (`object`): Extracted semantic units from output and ground truth.
 
-**analyzeStepResult:** (`object`): Detailed analysis of matches, contradictions, and extra information.
+**analyzeStepResult** (`object`): Detailed analysis of matches, contradictions, and extra information.
 
-**preprocessPrompt:** (`string`): The prompt used for semantic unit extraction.
+**preprocessPrompt** (`string`): The prompt used for semantic unit extraction.
 
-**analyzePrompt:** (`string`): The prompt used for similarity analysis.
+**analyzePrompt** (`string`): The prompt used for similarity analysis.
 
-**generateReasonPrompt:** (`string`): The prompt used for generating the explanation.
+**generateReasonPrompt** (`string`): The prompt used for generating the explanation.
 
 ## Scoring Details
 

package/.docs/reference/evals/bias.md

@@ -4,29 +4,29 @@ The `createBiasScorer()` function accepts a single options object with the follo
 
 ## Parameters
 
-**model:** (`LanguageModel`): Configuration for the model used to evaluate bias.
+**model** (`LanguageModel`): Configuration for the model used to evaluate bias.
 
-**scale:** (`number`): Maximum score value. (Default: `1`)
+**scale** (`number`): Maximum score value. (Default: `1`)
 
 This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but the return value includes LLM-specific fields as documented below.
 
 ## .run() Returns
 
-**runId:** (`string`): The id of the run (optional).
+**runId** (`string`): The id of the run (optional).
 
-**preprocessStepResult:** (`object`): Object with extracted opinions: { opinions: string\[] }
+**preprocessStepResult** (`object`): Object with extracted opinions: { opinions: string\[] }
 
-**preprocessPrompt:** (`string`): The prompt sent to the LLM for the preprocess step (optional).
+**preprocessPrompt** (`string`): The prompt sent to the LLM for the preprocess step (optional).
 
-**analyzeStepResult:** (`object`): Object with results: { results: Array<{ result: 'yes' | 'no', reason: string }> }
+**analyzeStepResult** (`object`): Object with results: { results: Array<{ result: 'yes' | 'no', reason: string }> }
 
-**analyzePrompt:** (`string`): The prompt sent to the LLM for the analyze step (optional).
+**analyzePrompt** (`string`): The prompt sent to the LLM for the analyze step (optional).
 
-**score:** (`number`): Bias score (0 to scale, default 0-1). Higher scores indicate more bias.
+**score** (`number`): Bias score (0 to scale, default 0-1). Higher scores indicate more bias.
 
-**reason:** (`string`): Explanation of the score.
+**reason** (`string`): Explanation of the score.
 
-**generateReasonPrompt:** (`string`): The prompt sent to the LLM for the generateReason step (optional).
+**generateReasonPrompt** (`string`): The prompt sent to the LLM for the generateReason step (optional).
 
 ## Bias Categories
 

package/.docs/reference/evals/completeness.md

@@ -10,11 +10,11 @@ This function returns an instance of the MastraScorer class. See the [MastraScor
 
 ## .run() Returns
 
-**runId:** (`string`): The id of the run (optional).
+**runId** (`string`): The id of the run (optional).
 
-**preprocessStepResult:** (`object`): Object with extracted elements and coverage details: { inputElements: string\[], outputElements: string\[], missingElements: string\[], elementCounts: { input: number, output: number } }
+**preprocessStepResult** (`object`): Object with extracted elements and coverage details: { inputElements: string\[], outputElements: string\[], missingElements: string\[], elementCounts: { input: number, output: number } }
 
-**score:** (`number`): Completeness score (0-1) representing the proportion of input elements covered in the output.
+**score** (`number`): Completeness score (0-1) representing the proportion of input elements covered in the output.
 
 The `.run()` method returns a result in the following shape:
 

package/.docs/reference/evals/content-similarity.md

@@ -6,21 +6,21 @@ The `createContentSimilarityScorer()` function measures the textual similarity b
 
 The `createContentSimilarityScorer()` function accepts a single options object with the following properties:
 
-**ignoreCase:** (`boolean`): Whether to ignore case differences when comparing strings. (Default: `true`)
+**ignoreCase** (`boolean`): Whether to ignore case differences when comparing strings. (Default: `true`)
 
-**ignoreWhitespace:** (`boolean`): Whether to normalize whitespace when comparing strings. (Default: `true`)
+**ignoreWhitespace** (`boolean`): Whether to normalize whitespace when comparing strings. (Default: `true`)
 
 This function returns an instance of the MastraScorer class. See the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer) for details on the `.run()` method and its input/output.
 
 ## .run() Returns
 
-**runId:** (`string`): The id of the run (optional).
+**runId** (`string`): The id of the run (optional).
 
-**preprocessStepResult:** (`object`): Object with processed input and output: { processedInput: string, processedOutput: string }
+**preprocessStepResult** (`object`): Object with processed input and output: { processedInput: string, processedOutput: string }
 
-**analyzeStepResult:** (`object`): Object with similarity: { similarity: number }
+**analyzeStepResult** (`object`): Object with similarity: { similarity: number }
 
-**score:** (`number`): Similarity score (0-1) where 1 indicates perfect similarity.
+**score** (`number`): Similarity score (0-1) where 1 indicates perfect similarity.
 
 ## Scoring Details
 

package/.docs/reference/evals/context-precision.md

@@ -22,17 +22,17 @@ Use when optimizing context selection for:
 
 ## Parameters
 
-**model:** (`MastraModelConfig`): The language model to use for evaluating context relevance
+**model** (`MastraModelConfig`): The language model to use for evaluating context relevance
 
-**options:** (`ContextPrecisionMetricOptions`): Configuration options for the scorer
+**options** (`ContextPrecisionMetricOptions`): Configuration options for the scorer
 
 **Note**: Either `context` or `contextExtractor` must be provided. If both are provided, `contextExtractor` takes precedence.
 
 ## .run() Returns
 
-**score:** (`number`): Mean Average Precision score between 0 and scale (default 0-1)
+**score** (`number`): Mean Average Precision score between 0 and scale (default 0-1)
 
-**reason:** (`string`): Human-readable explanation of the context precision evaluation
+**reason** (`string`): Human-readable explanation of the context precision evaluation
 
 ## Scoring Details
 

package/.docs/reference/evals/context-relevance.md

@@ -22,17 +22,17 @@ Use when optimizing for:
 
 ## Parameters
 
-**model:** (`MastraModelConfig`): The language model to use for evaluating context relevance
+**model** (`MastraModelConfig`): The language model to use for evaluating context relevance
 
-**options:** (`ContextRelevanceOptions`): Configuration options for the scorer
+**options** (`ContextRelevanceOptions`): Configuration options for the scorer
 
 Note: Either `context` or `contextExtractor` must be provided. If both are provided, `contextExtractor` takes precedence.
 
 ## .run() Returns
 
-**score:** (`number`): Weighted relevance score between 0 and scale (default 0-1)
+**score** (`number`): Weighted relevance score between 0 and scale (default 0-1)
 
-**reason:** (`string`): Human-readable explanation of the context relevance evaluation
+**reason** (`string`): Human-readable explanation of the context relevance evaluation
 
 ## Scoring Details
 

package/.docs/reference/evals/create-scorer.md

@@ -37,23 +37,21 @@ const scorer = createScorer({
 
 ## createScorer Options
 
-**id:** (`string`): Unique identifier for the scorer. Used as the name if \`name\` is not provided.
+**id** (`string`): Unique identifier for the scorer. Used as the name if \`name\` is not provided.
 
-**name?:** (`string`): Name of the scorer. Defaults to \`id\` if not provided.
+**name** (`string`): Name of the scorer. Defaults to \`id\` if not provided.
 
-**description:** (`string`): Description of what the scorer does.
+**description** (`string`): Description of what the scorer does.
 
-**judge?:** (`object`): Optional judge configuration for LLM-based steps. See Judge Object section below.
+**judge** (`object`): Optional judge configuration for LLM-based steps.
 
-**type?:** (`string`): Type specification for input/output. Use 'agent' for automatic agent types. For custom types, use the generic approach instead.
+**judge.model** (`LanguageModel`): The LLM model instance to use for evaluation.
 
-This function returns a scorer builder that you can chain step methods onto. See the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer) for details on the `.run()` method and its input/output.
-
-## Judge Object
+**judge.instructions** (`string`): System prompt/instructions for the LLM.
 
-**model:** (`LanguageModel`): The LLM model instance to use for evaluation.
+**type** (`string`): Type specification for input/output. Use 'agent' for automatic agent types. For custom types, use the generic approach instead.
 
-**instructions:** (`string`): System prompt/instructions for the LLM.
+This function returns a scorer builder that you can chain step methods onto. See the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer) for details on the `.run()` method and its input/output.
 
 The judge only runs for steps defined as **prompt objects** (`preprocess`, `analyze`, `generateScore`, `generateReason` in prompt mode). If you use function steps only, the judge is never called and there is no LLM output to inspect. In that case, any score/reason must be produced by your functions.
 
@@ -149,28 +147,28 @@ Optional preprocessing step that can extract or transform data before analysis.
 
 **Function Mode:** Function: `({ run, results }) => any`
 
-**run.input:** (`any`): Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. \`\[{ role: 'user', content: 'hello world' }]\`. If the scorer is used in a workflow, this will be the input of the workflow.
+**run.input** (`any`): Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. \`\[{ role: 'user', content: 'hello world' }]\`. If the scorer is used in a workflow, this will be the input of the workflow.
 
-**run.output:** (`any`): Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.
+**run.output** (`any`): Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.
 
-**run.runId:** (`string`): Unique identifier for this scoring run.
+**run.runId** (`string`): Unique identifier for this scoring run.
 
-**run.requestContext?:** (`object`): Request Context from the agent or workflow step being evaluated (optional).
+**run.requestContext** (`object`): Request Context from the agent or workflow step being evaluated (optional).
 
-**results:** (`object`): Empty object (no previous steps).
+**results** (`object`): Empty object (no previous steps).
 
 Returns: `any`\
 The method can return any value. The returned value will be available to subsequent steps as `preprocessStepResult`.
 
 **Prompt Object Mode:**
 
-**description:** (`string`): Description of what this preprocessing step does.
+**description** (`string`): Description of what this preprocessing step does.
 
-**outputSchema:** (`ZodSchema`): Zod schema for the expected output of the preprocess step.
+**outputSchema** (`ZodSchema`): Zod schema for the expected output of the preprocess step.
 
-**createPrompt:** (`function`): Function: ({ run, results }) => string. Returns the prompt for the LLM.
+**createPrompt** (`function`): Function: ({ run, results }) => string. Returns the prompt for the LLM.
 
-**judge?:** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
+**judge** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
 
 ### analyze
 
@@ -178,28 +176,28 @@ Optional analysis step that processes the input/output and any preprocessed data
 
 **Function Mode:** Function: `({ run, results }) => any`
 
-**run.input:** (`any`): Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. \`\[{ role: 'user', content: 'hello world' }]\`. If the scorer is used in a workflow, this will be the input of the workflow.
+**run.input** (`any`): Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. \`\[{ role: 'user', content: 'hello world' }]\`. If the scorer is used in a workflow, this will be the input of the workflow.
 
-**run.output:** (`any`): Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.
+**run.output** (`any`): Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.
 
-**run.runId:** (`string`): Unique identifier for this scoring run.
+**run.runId** (`string`): Unique identifier for this scoring run.
 
-**run.requestContext?:** (`object`): Request Context from the agent or workflow step being evaluated (optional).
+**run.requestContext** (`object`): Request Context from the agent or workflow step being evaluated (optional).
 
-**results.preprocessStepResult?:** (`any`): Result from preprocess step, if defined (optional).
+**results.preprocessStepResult** (`any`): Result from preprocess step, if defined (optional).
 
 Returns: `any`\
 The method can return any value. The returned value will be available to subsequent steps as `analyzeStepResult`.
 
 **Prompt Object Mode:**
 
-**description:** (`string`): Description of what this analysis step does.
+**description** (`string`): Description of what this analysis step does.
 
-**outputSchema:** (`ZodSchema`): Zod schema for the expected output of the analyze step.
+**outputSchema** (`ZodSchema`): Zod schema for the expected output of the analyze step.
 
-**createPrompt:** (`function`): Function: ({ run, results }) => string. Returns the prompt for the LLM.
+**createPrompt** (`function`): Function: ({ run, results }) => string. Returns the prompt for the LLM.
 
-**judge?:** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
+**judge** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
 
 ### generateScore
 
@@ -207,34 +205,34 @@ The method can return any value. The returned value will be available to subsequ
 
 **Function Mode:** Function: `({ run, results }) => number`
 
-**run.input:** (`any`): Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. \`\[{ role: 'user', content: 'hello world' }]\`. If the scorer is used in a workflow, this will be the input of the workflow.
+**run.input** (`any`): Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. \`\[{ role: 'user', content: 'hello world' }]\`. If the scorer is used in a workflow, this will be the input of the workflow.
 
-**run.output:** (`any`): Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.
+**run.output** (`any`): Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.
 
-**run.runId:** (`string`): Unique identifier for this scoring run.
+**run.runId** (`string`): Unique identifier for this scoring run.
 
-**run.requestContext?:** (`object`): Request Context from the agent or workflow step being evaluated (optional).
+**run.requestContext** (`object`): Request Context from the agent or workflow step being evaluated (optional).
 
-**results.preprocessStepResult?:** (`any`): Result from preprocess step, if defined (optional).
+**results.preprocessStepResult** (`any`): Result from preprocess step, if defined (optional).
 
-**results.analyzeStepResult?:** (`any`): Result from analyze step, if defined (optional).
+**results.analyzeStepResult** (`any`): Result from analyze step, if defined (optional).
 
 Returns: `number`\
 The method must return a numerical score.
 
 **Prompt Object Mode:**
 
-**description:** (`string`): Description of what this scoring step does.
+**description** (`string`): Description of what this scoring step does.
 
-**outputSchema:** (`ZodSchema`): Zod schema for the expected output of the generateScore step.
+**outputSchema** (`ZodSchema`): Zod schema for the expected output of the generateScore step.
 
-**createPrompt:** (`function`): Function: ({ run, results }) => string. Returns the prompt for the LLM.
+**createPrompt** (`function`): Function: ({ run, results }) => string. Returns the prompt for the LLM.
 
-**judge?:** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
+**judge** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
 
 When using prompt object mode, you must also provide a `calculateScore` function to convert the LLM output to a numerical score:
 
-**calculateScore:** (`function`): Function: ({ run, results, analyzeStepResult }) => number. Converts the LLM's structured output into a numerical score.
+**calculateScore** (`function`): Function: ({ run, results, analyzeStepResult }) => number. Converts the LLM's structured output into a numerical score.
 
 ### generateReason
 
@@ -242,29 +240,29 @@ Optional step that provides an explanation for the score.
 
 **Function Mode:** Function: `({ run, results, score }) => string`
 
-**run.input:** (`any`): Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. \`\[{ role: 'user', content: 'hello world' }]\`. If the scorer is used in a workflow, this will be the input of the workflow.
+**run.input** (`any`): Input records provided to the scorer. If the scorer is added to an agent, this will be an array of user messages, e.g. \`\[{ role: 'user', content: 'hello world' }]\`. If the scorer is used in a workflow, this will be the input of the workflow.
 
-**run.output:** (`any`): Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.
+**run.output** (`any`): Output record provided to the scorer. For agents, this is usually the agent's response. For workflows, this is the workflow's output.
 
-**run.runId:** (`string`): Unique identifier for this scoring run.
+**run.runId** (`string`): Unique identifier for this scoring run.
 
-**run.requestContext?:** (`object`): Request Context from the agent or workflow step being evaluated (optional).
+**run.requestContext** (`object`): Request Context from the agent or workflow step being evaluated (optional).
 
-**results.preprocessStepResult?:** (`any`): Result from preprocess step, if defined (optional).
+**results.preprocessStepResult** (`any`): Result from preprocess step, if defined (optional).
 
-**results.analyzeStepResult?:** (`any`): Result from analyze step, if defined (optional).
+**results.analyzeStepResult** (`any`): Result from analyze step, if defined (optional).
 
-**score:** (`number`): Score computed by the generateScore step.
+**score** (`number`): Score computed by the generateScore step.
 
 Returns: `string`\
 The method must return a string explaining the score.
 
 **Prompt Object Mode:**
 
-**description:** (`string`): Description of what this reasoning step does.
+**description** (`string`): Description of what this reasoning step does.
 
-**createPrompt:** (`function`): Function: ({ run, results, score }) => string. Returns the prompt for the LLM.
+**createPrompt** (`function`): Function: ({ run, results, score }) => string. Returns the prompt for the LLM.
 
-**judge?:** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
+**judge** (`object`): (Optional) LLM judge for this step (can override main judge). See Judge Object section.
 
 All step functions can be async.

package/.docs/reference/evals/faithfulness.md

@@ -6,31 +6,31 @@ The `createFaithfulnessScorer()` function evaluates how factually accurate an LL
 
 The `createFaithfulnessScorer()` function accepts a single options object with the following properties:
 
-**model:** (`LanguageModel`): Configuration for the model used to evaluate faithfulness.
+**model** (`LanguageModel`): Configuration for the model used to evaluate faithfulness.
 
-**context:** (`string[]`): Array of context chunks against which the output's claims will be verified.
+**context** (`string[]`): Array of context chunks against which the output's claims will be verified.
 
-**scale:** (`number`): The maximum score value. The final score will be normalized to this scale. (Default: `1`)
+**scale** (`number`): The maximum score value. The final score will be normalized to this scale. (Default: `1`)
 
 This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but the return value includes LLM-specific fields as documented below.
 
 ## .run() Returns
 
-**runId:** (`string`): The id of the run (optional).
+**runId** (`string`): The id of the run (optional).
 
-**preprocessStepResult:** (`string[]`): Array of extracted claims from the output.
+**preprocessStepResult** (`string[]`): Array of extracted claims from the output.
 
-**preprocessPrompt:** (`string`): The prompt sent to the LLM for the preprocess step (optional).
+**preprocessPrompt** (`string`): The prompt sent to the LLM for the preprocess step (optional).
 
-**analyzeStepResult:** (`object`): Object with verdicts: { verdicts: Array<{ verdict: 'yes' | 'no' | 'unsure', reason: string }> }
+**analyzeStepResult** (`object`): Object with verdicts: { verdicts: Array<{ verdict: 'yes' | 'no' | 'unsure', reason: string }> }
 
-**analyzePrompt:** (`string`): The prompt sent to the LLM for the analyze step (optional).
+**analyzePrompt** (`string`): The prompt sent to the LLM for the analyze step (optional).
 
-**score:** (`number`): A score between 0 and the configured scale, representing the proportion of claims that are supported by the context.
+**score** (`number`): A score between 0 and the configured scale, representing the proportion of claims that are supported by the context.
 
-**reason:** (`string`): A detailed explanation of the score, including which claims were supported, contradicted, or marked as unsure.
+**reason** (`string`): A detailed explanation of the score, including which claims were supported, contradicted, or marked as unsure.
 
-**generateReasonPrompt:** (`string`): The prompt sent to the LLM for the generateReason step (optional).
+**generateReasonPrompt** (`string`): The prompt sent to the LLM for the generateReason step (optional).
 
 ## Scoring Details
 

package/.docs/reference/evals/hallucination.md

@@ -6,45 +6,41 @@ The `createHallucinationScorer()` function evaluates whether an LLM generates fa
 
 The `createHallucinationScorer()` function accepts a single options object with the following properties:
 
-**model:** (`LanguageModel`): Configuration for the model used to evaluate hallucination.
+**model** (`LanguageModel`): Configuration for the model used to evaluate hallucination.
 
-**options.scale:** (`number`): Maximum score value. (Default: `1`)
+**options.scale** (`number`): Maximum score value. (Default: `1`)
 
-**options.context:** (`string[]`): Static context strings to use as ground truth for hallucination detection.
+**options.context** (`string[]`): Static context strings to use as ground truth for hallucination detection.
 
-**options.getContext:** (`(params: GetContextParams) => string[] | Promise<string[]>`): A hook to dynamically resolve context at runtime. Takes priority over static context. Useful for live scoring where context (like tool results) is only available when the scorer runs.
+**options.getContext** (`(params: GetContextParams) => string[] | Promise<string[]>`): A hook to dynamically resolve context at runtime. Takes priority over static context. Useful for live scoring where context (like tool results) is only available when the scorer runs.
 
-This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but the return value includes LLM-specific fields as documented below.
-
-### GetContextParams
+**options.getContext.run** (`GetContextRun`): The scorer run containing input, output, runId, requestContext, and tracingContext.
 
-The `getContext` hook receives the following parameters:
+**options.getContext.results** (`Record<string, any>`): Accumulated results from previous steps (e.g., preprocessStepResult with extracted claims).
 
-**run:** (`GetContextRun`): The scorer run containing input, output, runId, requestContext, and tracingContext.
+**options.getContext.score** (`number`): The computed score. Only present when called from the generateReason step.
 
-**results:** (`Record<string, any>`): Accumulated results from previous steps (e.g., preprocessStepResult with extracted claims).
+**options.getContext.step** (`'analyze' | 'generateReason'`): Which step is calling the hook. Useful for caching context between calls.
 
-**score:** (`number`): The computed score. Only present when called from the generateReason step.
-
-**step:** (`'analyze' | 'generateReason'`): Which step is calling the hook. Useful for caching context between calls.
+This function returns an instance of the MastraScorer class. The `.run()` method accepts the same input as other scorers (see the [MastraScorer reference](https://mastra.ai/reference/evals/mastra-scorer)), but the return value includes LLM-specific fields as documented below.
 
 ## .run() Returns
 
-**runId:** (`string`): The id of the run (optional).
+**runId** (`string`): The id of the run (optional).
 
-**preprocessStepResult:** (`object`): Object with extracted claims: { claims: string\[] }
+**preprocessStepResult** (`object`): Object with extracted claims: { claims: string\[] }
 
-**preprocessPrompt:** (`string`): The prompt sent to the LLM for the preprocess step (optional).
+**preprocessPrompt** (`string`): The prompt sent to the LLM for the preprocess step (optional).
 
-**analyzeStepResult:** (`object`): Object with verdicts: { verdicts: Array<{ statement: string, verdict: 'yes' | 'no', reason: string }> }
+**analyzeStepResult** (`object`): Object with verdicts: { verdicts: Array<{ statement: string, verdict: 'yes' | 'no', reason: string }> }
 
-**analyzePrompt:** (`string`): The prompt sent to the LLM for the analyze step (optional).
+**analyzePrompt** (`string`): The prompt sent to the LLM for the analyze step (optional).
 
-**score:** (`number`): Hallucination score (0 to scale, default 0-1).
+**score** (`number`): Hallucination score (0 to scale, default 0-1).
 
-**reason:** (`string`): Detailed explanation of the score and identified contradictions.
+**reason** (`string`): Detailed explanation of the score and identified contradictions.
 
-**generateReasonPrompt:** (`string`): The prompt sent to the LLM for the generateReason step (optional).
+**generateReasonPrompt** (`string`): The prompt sent to the LLM for the generateReason step (optional).
 
 ## Scoring Details
 

package/.docs/reference/evals/keyword-coverage.md

@@ -10,13 +10,13 @@ This function returns an instance of the MastraScorer class. See the [MastraScor
 
 ## .run() Returns
 
-**runId:** (`string`): The id of the run (optional).
+**runId** (`string`): The id of the run (optional).
 
-**preprocessStepResult:** (`object`): Object with extracted keywords: { referenceKeywords: Set\<string>, responseKeywords: Set\<string> }
+**preprocessStepResult** (`object`): Object with extracted keywords: { referenceKeywords: Set\<string>, responseKeywords: Set\<string> }
 
-**analyzeStepResult:** (`object`): Object with keyword coverage: { totalKeywords: number, matchedKeywords: number }
+**analyzeStepResult** (`object`): Object with keyword coverage: { totalKeywords: number, matchedKeywords: number }
 
-**score:** (`number`): Coverage score (0-1) representing the proportion of matched keywords.
+**score** (`number`): Coverage score (0-1) representing the proportion of matched keywords.
 
 `.run()` returns a result in the following shape:
 

package/.docs/reference/evals/mastra-scorer.md

@@ -39,35 +39,35 @@ const result = await scorer.run({
 
 ## .run() Input
 
-**input:** (`any`): Input data to be evaluated. Can be any type depending on your scorer's requirements.
+**input** (`any`): Input data to be evaluated. Can be any type depending on your scorer's requirements.
 
-**output:** (`any`): Output data to be evaluated. Can be any type depending on your scorer's requirements.
+**output** (`any`): Output data to be evaluated. Can be any type depending on your scorer's requirements.
 
-**runId:** (`string`): Optional unique identifier for this scoring run.
+**runId** (`string`): Optional unique identifier for this scoring run.
 
-**requestContext:** (`any`): Optional request context from the agent or workflow step being evaluated.
+**requestContext** (`any`): Optional request context from the agent or workflow step being evaluated.
 
-**groundTruth:** (`any`): Optional expected or reference output for comparison during scoring. Automatically passed when using runEvals.
+**groundTruth** (`any`): Optional expected or reference output for comparison during scoring. Automatically passed when using runEvals.
 
 ## .run() Returns
 
-**runId:** (`string`): The unique identifier for this scoring run.
+**runId** (`string`): The unique identifier for this scoring run.
 
-**score:** (`number`): Numerical score computed by the generateScore step.
+**score** (`number`): Numerical score computed by the generateScore step.
 
-**reason:** (`string`): Explanation for the score, if generateReason step was defined (optional).
+**reason** (`string`): Explanation for the score, if generateReason step was defined (optional).
 
-**preprocessStepResult:** (`any`): Result of the preprocess step, if defined (optional).
+**preprocessStepResult** (`any`): Result of the preprocess step, if defined (optional).
 
-**analyzeStepResult:** (`any`): Result of the analyze step, if defined (optional).
+**analyzeStepResult** (`any`): Result of the analyze step, if defined (optional).
 
-**preprocessPrompt:** (`string`): Preprocess prompt, if defined (optional).
+**preprocessPrompt** (`string`): Preprocess prompt, if defined (optional).
 
-**analyzePrompt:** (`string`): Analyze prompt, if defined (optional).
+**analyzePrompt** (`string`): Analyze prompt, if defined (optional).
 
-**generateScorePrompt:** (`string`): Generate score prompt, if defined (optional).
+**generateScorePrompt** (`string`): Generate score prompt, if defined (optional).
 
-**generateReasonPrompt:** (`string`): Generate reason prompt, if defined (optional).
+**generateReasonPrompt** (`string`): Generate reason prompt, if defined (optional).
 
 ## Step Execution Flow
 

package/.docs/reference/evals/noise-sensitivity.md

@@ -13,9 +13,9 @@ Before using the noise sensitivity scorer, prepare your test data:
 
 ## Parameters
 
-**model:** (`MastraModelConfig`): The language model to use for evaluating noise sensitivity
+**model** (`MastraModelConfig`): The language model to use for evaluating noise sensitivity
 
-**options:** (`NoiseSensitivityOptions`): Configuration options for the scorer
+**options** (`NoiseSensitivityOptions`): Configuration options for the scorer
 
 ## CI/Testing Requirements
 
@@ -82,9 +82,9 @@ describe('Agent Noise Resistance Tests', () => {
 
 ## .run() Returns
 
-**score:** (`number`): Robustness score between 0 and 1 (1.0 = completely robust, 0.0 = severely compromised)
+**score** (`number`): Robustness score between 0 and 1 (1.0 = completely robust, 0.0 = severely compromised)
 
-**reason:** (`string`): Human-readable explanation of how noise affected the agent's response
+**reason** (`string`): Human-readable explanation of how noise affected the agent's response
 
 ## Evaluation Dimensions
 

package/.docs/reference/evals/prompt-alignment.md

@@ -4,15 +4,15 @@ The `createPromptAlignmentScorerLLM()` function creates a scorer that evaluates
 
 ## Parameters
 
-**model:** (`MastraModelConfig`): The language model to use for evaluating prompt-response alignment
+**model** (`MastraModelConfig`): The language model to use for evaluating prompt-response alignment
 
-**options:** (`PromptAlignmentOptions`): Configuration options for the scorer
+**options** (`PromptAlignmentOptions`): Configuration options for the scorer
 
 ## .run() Returns
 
-**score:** (`number`): Multi-dimensional alignment score between 0 and scale (default 0-1)
+**score** (`number`): Multi-dimensional alignment score between 0 and scale (default 0-1)
 
-**reason:** (`string`): Human-readable explanation of the prompt alignment evaluation with detailed breakdown
+**reason** (`string`): Human-readable explanation of the prompt alignment evaluation with detailed breakdown
 
 `.run()` returns a result in the following shape: