diff --git a/docs/_static/llama-stack-spec.html b/docs/_static/llama-stack-spec.html
index 3b8672607..0c82fc670 100644
--- a/docs/_static/llama-stack-spec.html
+++ b/docs/_static/llama-stack-spec.html
@@ -11294,19 +11294,23 @@
                 "type": "object",
                 "properties": {
                     "query_generator_config": {
-                        "$ref": "#/components/schemas/RAGQueryGeneratorConfig"
+                        "$ref": "#/components/schemas/RAGQueryGeneratorConfig",
+                        "description": "Configuration for the query generator."
                     },
                     "max_tokens_in_context": {
                         "type": "integer",
-                        "default": 4096
+                        "default": 4096,
+                        "description": "Maximum number of tokens in the context."
                     },
                     "max_chunks": {
                         "type": "integer",
-                        "default": 5
+                        "default": 5,
+                        "description": "Maximum number of chunks to retrieve."
                     },
                     "chunk_template": {
                         "type": "string",
-                        "default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n"
+                        "default": "Result {index}\nContent: {chunk.content}\nMetadata: {metadata}\n",
+                        "description": "Template for formatting each retrieved chunk in the context."
                     }
                 },
                 "additionalProperties": false,
@@ -11316,7 +11320,8 @@
                     "max_chunks",
                     "chunk_template"
                 ],
-                "title": "RAGQueryConfig"
+                "title": "RAGQueryConfig",
+                "description": "Configuration for the RAG query generation."
             },
             "RAGQueryGeneratorConfig": {
                 "oneOf": [
diff --git a/docs/_static/llama-stack-spec.yaml b/docs/_static/llama-stack-spec.yaml
index f820b9ccd..c9de5316c 100644
--- a/docs/_static/llama-stack-spec.yaml
+++ b/docs/_static/llama-stack-spec.yaml
@@ -7794,12 +7794,15 @@ components:
       properties:
         query_generator_config:
           $ref: '#/components/schemas/RAGQueryGeneratorConfig'
+          description: Configuration for the query generator.
         max_tokens_in_context:
           type: integer
           default: 4096
+          description: Maximum number of tokens in the context.
         max_chunks:
           type: integer
           default: 5
+          description: Maximum number of chunks to retrieve.
         chunk_template:
           type: string
           default: >
@@ -7808,6 +7811,8 @@ components:
             Content: {chunk.content}
 
             Metadata: {metadata}
+          description: >-
+            Template for formatting each retrieved chunk in the context.
       additionalProperties: false
       required:
         - query_generator_config
@@ -7815,6 +7820,8 @@ components:
         - max_chunks
         - chunk_template
       title: RAGQueryConfig
+      description: >-
+        Configuration for the RAG query generation.
     RAGQueryGeneratorConfig:
       oneOf:
         - $ref: '#/components/schemas/DefaultRAGQueryGeneratorConfig'
diff --git a/llama_stack/apis/tools/rag_tool.py b/llama_stack/apis/tools/rag_tool.py
index 6c94507be..f20a882e7 100644
--- a/llama_stack/apis/tools/rag_tool.py
+++ b/llama_stack/apis/tools/rag_tool.py
@@ -67,6 +67,15 @@ register_schema(RAGQueryGeneratorConfig, name="RAGQueryGeneratorConfig")
 
 @json_schema_type
 class RAGQueryConfig(BaseModel):
+    """
+    Configuration for the RAG query generation.
+
+    :param query_generator_config: Configuration for the query generator.
+    :param max_tokens_in_context: Maximum number of tokens in the context.
+    :param max_chunks: Maximum number of chunks to retrieve.
+    :param chunk_template: Template for formatting each retrieved chunk in the context.
+    """
+
     # This config defines how a query is generated using the messages
     # for memory bank retrieval.
     query_generator_config: RAGQueryGeneratorConfig = Field(default=DefaultRAGQueryGeneratorConfig())