Update token capacity (optimal 500k) and remove manual schema registration fallback

Author: Dongbumlee

docs/CustomizingAzdParameters.md

@@ -16,7 +16,7 @@ By default this template will use the environment name as the prefix to prevent
 | `AZURE_ENV_MODEL_DEPLOYMENT_TYPE`      | string  | `GlobalStandard`          | Defines the model deployment type. Allowed: `Standard`, `GlobalStandard`.             |
 | `AZURE_ENV_MODEL_NAME`                 | string  | `gpt-5.1`                 | Specifies the GPT model name. Default: `gpt-5.1`.                                     |
 | `AZURE_ENV_MODEL_VERSION`              | string  | `2025-04-14`              | Specifies the GPT model version.                                                      |
-| `AZURE_ENV_MODEL_CAPACITY`             | integer | `300`                       | Sets the model capacity (minimum 1). Recommended: 300 for multi-document claim processing. |
+| `AZURE_ENV_MODEL_CAPACITY`             | integer | `300`                       | Sets the model capacity (minimum 1). Default: 300. Optimal: 500 for multi-document claim processing. |
 | `AZURE_ENV_CONTAINER_REGISTRY_ENDPOINT` | string  | `cpscontainerreg.azurecr.io` | Sets the public container image endpoint for pulling pre-built images.                |
 | `AZURE_ENV_CONTAINER_IMAGE_TAG`        | string  | `latest`                    | Sets the container image tag (e.g., `latest`, `dev`, `hotfix`).                       |
 | `AZURE_ENV_LOG_ANALYTICS_WORKSPACE_ID` | string  | Guide to get your [Existing Workspace ID](/docs/re-use-log-analytics.md) | Reuses an existing Log Analytics Workspace instead of provisioning a new one.         |

docs/DeploymentGuide.md

@@ -66,7 +66,7 @@ Ensure you have access to an [Azure subscription](https://azure.microsoft.com/fr
 
 **Recommended Configuration:**
 - **Default:** 300k tokens
-- **Optimal:** 300k tokens (recommended for multi-document claim processing)
+- **Optimal:** 500k tokens (recommended for multi-document claim processing)
 
 > **Note:** When you run `azd up`, the deployment will automatically show you regions with available quota, so this pre-check is optional but helpful for planning purposes. You can customize these settings later in [Step 3.3: Advanced Configuration](#33-advanced-configuration-optional).
 
@@ -306,7 +306,7 @@ After successful deployment:
 
  > Want to customize the schemas for your own documents? [Learn more about adding your own schemas here.](./CustomizeSchemaData.md)
 
-Schema registration happens **automatically** as part of the `azd up` post-provisioning hook. After infrastructure is deployed, the hook:
+Schema registration happens **automatically** as part of the `azd up` post-provisioning hook — no manual steps required. After infrastructure is deployed, the hook:
 
 1. Waits for the API container app to be ready
 2. Registers the sample schema files (auto claim, damaged car image, police report, repair estimate)
@@ -317,12 +317,6 @@ You should see output like this in the terminal:
 
 ![schema file registration](./images/SchemaFileRegistration.png)  
 
-> **If registration was skipped** (e.g. the API wasn't ready in time), you can run it manually:
-> ```bash
-> cd src/ContentProcessorAPI/samples/schemas
-> python register_schema.py https://<< API Service Endpoint>> schema_info.json
-> ```
-
 ### 5.2 Configure Authentication (Required)
 
 **This step is mandatory for application access:**

docs/quota_check.md

@@ -1,7 +1,7 @@
 ## Check Quota Availability Before Deployment
 
 Before deploying the accelerator, **ensure sufficient quota availability** for the required model.
-> **For Global Standard | GPT-5.1 — the capacity to at least 300K tokens for optimal multi-document claim processing.**
+> **For Global Standard | GPT-5.1 — the capacity to at least 300K tokens (default). 500K tokens recommended for optimal multi-document claim processing.**
 
 ### Login if you have not done so already
 ```