DOAJ MCP provides 4 read-only tools with complete input schemas and basic descriptions. All tools have proper verb-noun naming (search_*, get_*) and required parameters are marked. However, descriptions are minimal (10-50 chars), lack context on when to use each tool, and parameter descriptions are sparse. Output schemas are undocumented, LLMs cannot predict response structure for chaining. No error handling guidance. Pagination is implemented but not clearly explained in descriptions. This is a typical community server: functional but underspecified for LLM reasoning.

• Expand tool descriptions to 100-200 chars. Example: 'search_articles: Search peer-reviewed open-access articles by title, abstract, author, year, or free text. Returns paginated results with article metadata. Use this to discover articles; use get_article to fetch full details by DOAJ ID.'
• Document output schemas for each tool. Specify response fields (e.g., results[], total, page, page_size) and their types. Include example response snippets in comments.
• Add parameter constraints to descriptions. Example: 'sort: Sort results by field and direction (e.g., "created_date:desc", "relevance:asc"). Valid fields: created_date, title, relevance.'
• Enhance error messages with recovery guidance. Example: Instead of 'DOAJ: not found', return 'Article not found. Verify the DOAJ ID is correct, or use search_articles to find the article by title/author.'
• Document pagination behavior explicitly. Example: 'page: 1-based page number (default 1). page_size: Results per page, 1-100 (default 10). Response includes total count and current page for iteration.'