Server has 5 well-named tools with clear descriptions and complete input schemas. All tools follow verb_noun naming (search_, lookup_, get_). Descriptions are substantive (100-200 chars, within baseline 194 avg). Input schemas use proper JSON Schema with types and descriptions for all parameters. However, output schemas are completely undocumented, LLMs cannot plan downstream calls or extract structured data. No error handling guidance, no parameter constraints (enums), no pagination documentation despite tools returning lists. Missing idempotency hints for read-only operations. Parameter descriptions lack format/range constraints (e.g., country code format, minDiscount bounds).

• Document output schemas for all 5 tools. Example for get_game_prices: 'Returns {games: [{id, title, deals: [{shop_name, current_price, regular_price, discount_percent, url}]}]}'. Include field types and what each field means.
• Add enum constraints: country parameter should list valid ISO 3166-1 codes (US, GB, DE, etc.). minDiscount should have min=0, max=100. limit should have min=1, max=50.
• Enhance error messages with recovery guidance. Replace 'ITAD API HTTP Error 404' with 'Game UUID not found. Verify the UUID or call search_games() to find the correct ID.'
• Document pagination for search_games and get_active_deals. Add limit and offset parameters if the API supports them, or state max results returned and offer guidance on filtering.
• Make lookup_game require at least one of steamAppId or title. Add description: 'Provide either a Steam AppID (numeric) or game title (string). If both provided, steamAppId takes precedence.'