Readarr MCP has well-structured tool definitions with consistent naming (verb_noun pattern), clear descriptions (avg ~120 chars), and complete JSON schemas with type constraints. All 15 tools are explicitly registered with inputSchema. However, output schemas are entirely undocumented, LLMs cannot predict response structure for downstream chaining. Error handling is minimal; no recovery guidance or actionable error messages. Parameter descriptions lack format constraints (e.g., 'limit' has no min/max bounds). No tool annotations (readOnlyHint/destructiveHint) despite clear risk stratification. Missing idempotency guidance for write operations.

• Document output schemas for all tools. E.g., readarr_search_authors should declare: {type: 'object', properties: {results: {type: 'array', items: {type: 'object', properties: {foreignAuthorId: {type: 'string'}, authorName: {type: 'string'}, ...}}}}}. This enables LLM to extract foreignAuthorId for readarr_add_author.
• Add min/max constraints to numeric parameters. E.g., limit: {type: 'number', minimum: 1, maximum: 500, description: 'Max results (default: 20, range: 1-500)'}. Prevents absurd values.
• Implement tool annotations in tool definitions. Add readOnlyHint: true to all readarr_get_* tools, destructiveHint: true to readarr_delete_author, idempotentHint: true to readarr_refresh_author. This signals safety properties to MCP clients.
• Enhance error messages with recovery guidance. E.g., if readarr_get_author returns 404, catch and return: 'Author ID 999 not found. Try readarr_search_authors("author name") to find the correct ID, or readarr_get_all_authors() to list available authors.'
• Add dry-run support to readarr_delete_author. Add optional dryRun: {type: 'boolean', description: 'Preview deletion without executing (default: false)'}. Return what would be deleted before confirming.