Server has 13 tools with basic schemas and descriptions in German. All tools have input schemas with type definitions and descriptions present. However, descriptions are often generic or lack actionable context for LLM selection. No output schemas documented. Error handling is minimal, most tools return error dicts but lack recovery guidance. Parameter descriptions exist but many lack constraints (enums, ranges, formats). No tool annotations (readOnlyHint, destructiveHint). Composition is reasonable (verb_noun naming, single responsibility), but descriptions don't explain WHEN to use each tool vs alternatives. Average description length ~120 chars (below 194 baseline), many under 50 chars.

• Document output schemas for all data-returning tools. E.g., shopify_get_products should specify: {products: [{id, title, price, inventory_count}], total_count, next_cursor}. This enables LLM planning and field extraction.
• Expand descriptions to 100-200 chars with WHEN/WHY context. E.g., 'Fetch products from a connected Shopify store. Use this after connect_shopify to list available inventory. Returns product ID, title, price, and stock levels for pagination and filtering.'
• Add enum constraints to string parameters. E.g., shopify_get_orders status param: enum=[any, open, closed, cancelled]. Replace free-form 'search' param in wordpress_get_posts with explicit search_term and add format/length constraints.
• Add tool annotations via FastMCP. Mark connect_* tools with destructiveHint=true (modifies state). Mark all get_* and list_* tools with readOnlyHint=true. Mark idempotent tools with idempotentHint=true.
• Enhance error responses with recovery hints. E.g., 'Connector "shopify-store" not found. Available connectors: [list]. Call list_connectors() to see all configured connections, or connect_shopify() to add a new one.'