This server has a single tool 'execute_skill_action' with virtually no definition. The tool description is a generic 1-liner (47 chars) that does not explain what the tool does, when to use it, or what it returns. No input schema is visible in the source code, the mcp_server.py file only prints a JSON status message and does not register any tool with parameters or schemas. The client.py and example_usage.py files show a HeadlessRetailDynamicContentExperienceCmsClient class with a generate_shoppable_lookbook() method, but this is NOT connected to the MCP tool definition. The tool appears to be inferred rather than explicitly registered with a schema.

• Add explicit tool registration in mcp_server.py with full JSON Schema input definition. Include parameter names, types (string, number, array, object), descriptions, and constraints (enums, min/max, patterns).
• Expand tool description to 100-200 characters. Example: 'Generate a shoppable lookbook with rich media hotspots, product SKUs, and responsive image variants for headless retail CMS delivery. Accepts campaign theme and target geography.'
• Rename tool from 'execute_skill_action' to a specific verb_noun pair like 'generate_shoppable_lookbook' or 'create_dynamic_content_block'. This clarifies intent for LLM tool selection.
• Document the output schema with all fields, types, and descriptions. Include: content_block_id (string), campaign_theme (string), rich_media_hotspots (array of objects with x_pct, y_pct, sku, price), headless_graphql_content_delivery_url (string), image_rendering_web_vitals_lcp_ms (number), dynamic_device_responsive_variants (array of strings).
• Add parameter descriptions for 'campaign_theme' (string, e.g. 'Autumn Layering Essentials') and 'target_geo' (enum: EU_GB, US_EAST, APAC, etc.). Specify constraints and valid values.