diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index cd514668f..7aaf19c5d 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -4053,28 +4053,33 @@
                 "type": "object",
                 "properties": {
                     "strategy": {
-                        "$ref": "#/components/schemas/SamplingStrategy"
+                        "$ref": "#/components/schemas/SamplingStrategy",
+                        "description": "The sampling strategy."
                     },
                     "max_tokens": {
                         "type": "integer",
-                        "default": 0
+                        "default": 0,
+                        "description": "The maximum number of tokens that can be generated in the completion. The token count of your prompt plus max_tokens cannot exceed the model's context length."
                     },
                     "repetition_penalty": {
                         "type": "number",
-                        "default": 1.0
+                        "default": 1.0,
+                        "description": "Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics."
                     },
                     "stop": {
                         "type": "array",
                         "items": {
                             "type": "string"
-                        }
+                        },
+                        "description": "Up to 4 sequences where the API will stop generating further tokens. The returned text will not contain the stop sequence."
                     }
                 },
                 "additionalProperties": false,
                 "required": [
                     "strategy"
                 ],
-                "title": "SamplingParams"
+                "title": "SamplingParams",
+                "description": "Sampling parameters."
             },
             "SamplingStrategy": {
                 "oneOf": [
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index 6c96c3805..d25b9afb3 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -2787,20 +2787,33 @@ components:
       properties:
         strategy:
           $ref: '#/components/schemas/SamplingStrategy'
+          description: The sampling strategy.
         max_tokens:
           type: integer
           default: 0
+          description: >-
+            The maximum number of tokens that can be generated in the completion.
+            The token count of your prompt plus max_tokens cannot exceed the model's
+            context length.
         repetition_penalty:
           type: number
           default: 1.0
+          description: >-
+            Number between -2.0 and 2.0. Positive values penalize new tokens based
+            on whether they appear in the text so far, increasing the model's likelihood
+            to talk about new topics.
         stop:
           type: array
           items:
             type: string
+          description: >-
+            Up to 4 sequences where the API will stop generating further tokens. The
+            returned text will not contain the stop sequence.
       additionalProperties: false
       required:
         - strategy
       title: SamplingParams
+      description: Sampling parameters.
     SamplingStrategy:
       oneOf:
         - $ref: '#/components/schemas/GreedySamplingStrategy'