Single tool 'add' with basic schema and minimal description. Tool has proper input schema with typed parameters (a: number, b: number) and explicit output schema, but description is extremely brief (11 characters, below the 20-character hard minimum for scoring above 0-20 range). No parameter descriptions provided. Tool naming is a verb (add) which is correct per pattern:tool, but the overall definition lacks the context and clarity needed for LLM selection and proper invocation. The server demonstrates correct schema structure (Zod-based, properly typed) but fails to meet minimum documentation standards for production readiness. Resource 'greeting' is present but not evaluated as a tool per the rubric focus.
Adds two numbers
Tool description far too brief ('Adds two numbers' = 11 chars). Descriptions under 20 characters cannot score above 0-20. Must expand to explain WHEN to use this tool, any prerequisites, and what it returns in plain language for LLM selection.
Input parameters 'a' and 'b' have no descriptions. Per pattern:tool-description, every parameter requires a non-empty description explaining what it controls. LLM cannot infer that 'a' and 'b' are operands without explicit text.
Output schema is present in code (outputSchema: { result: z.number() }) but not documented for the LLM in any user-facing description. LLMs should know what fields to expect in the response.
No error handling guidance. Tool description does not explain what happens on invalid input (e.g., non-numeric values, NaN, Infinity) or how the LLM should recover.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-22 | F | 49 | 2025-06-18+ | v2 |
| 2026-03-09 | F | 0 | - | v1 |
Tool name 'add' is generic and does not follow verb_noun convention. Better names: 'add_numbers', 'calculate_sum'. Current name alone does not disambiguate from similar arithmetic tools.