An MCP server deployed on Cloudflare Workers with OAuth 2.0 authentication support, demonstrating remote MCP server capabilities with authorization flows
Single tool 'add' has a basic schema with typed parameters (a, b as numbers) and descriptions, but falls short of production quality. No output schema documented. No error handling guidance. Tool is trivial (arithmetic) and lacks real-world complexity, but the definition pattern is weak: description should explain WHEN to use this tool, what it returns, and any edge cases. Parameter descriptions are present but generic. No pagination, no idempotent hints, no recovery guidance.
Adds two numbers together
Tool description is 18 characters ('Adds two numbers together'), below 20-char minimum. Lacks WHEN to use, WHAT it returns, and prerequisites.
No output schema documented. LLMs cannot plan downstream calls or extract results without knowing the response structure. Rubric requires 100% of A+ tools to have documented return types.
No error handling or recovery guidance. If addition fails (e.g., overflow, invalid input), LLM has no actionable next step. Rubric requires error responses to guide recovery.
Parameter descriptions ('First number to add', 'Second number to add') are generic and do not specify format, range, or constraints. Rubric baseline: average param annotation 72 chars; these are ~20 chars each.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 42 | 2026-07-28+ | v2 |
Tool name 'add' lacks verb_noun clarity. While 'add' is a verb, a more specific name like 'add_numbers' or 'calculate_sum' would better signal intent and distinguish from other arithmetic operations.