MCP server for accessing Gousto cookbook recipes, categories, and recipe details via HTTP transport
Server has 4 tools with complete input schemas and descriptions. Naming follows verb_noun convention (get_, search_). Descriptions are present but generic (avg 80 chars, below 194-char baseline). Parameter descriptions exist but lack detail on constraints, formats, and use cases. No output schemas documented. No error handling guidance. Tool composition is sound (single responsibility), but parameter naming could be more explicit (e.g., 'recipeSlug' vs 'recipe_slug' inconsistency). Missing idempotency hints and recovery guidance.
Get detailed information about a specific recipe
Get a list of recipes from a specific category
Search for recipes by keyword (example chicken, pepper, steak etc) across the top 900 rated or more recipes
Search for recipes by keyword across categories
Tool naming inconsistency: 'search-top-recipes' uses hyphens while others use underscores. Inconsistent naming confuses LLM tool selection and violates verb_noun convention.
No output schemas documented. LLMs cannot plan downstream operations or extract required fields without knowing response structure. All tools return Recipe/RecipeDetail objects but this is not declared in tool definitions.
Parameter descriptions lack actionable constraints. 'limit' has min/max but no guidance on typical values or performance impact. 'keyword' has no length limits or special character handling documented.
No error handling guidance. Tools may fail (API down, invalid slug, rate limit) but return no recovery hints. LLM cannot determine if error is retryable or user-fixable.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | C | 60 | 2026-07-28+ | v2 |
Parameter naming mixes camelCase ('recipeSlug') and snake_case ('pagination'). Inconsistent naming increases LLM confusion and violates tool interface conventions.