MCP server with OAuth authentication and a simple arithmetic tool
Single tool 'add' has a clear, concise description (28 chars) and properly typed input schema with parameter descriptions. However, the description is below the 50-200 char baseline for LLM-optimized descriptions, lacks context on when/why to use it, and provides no output schema documentation. No error handling guidance. Tool is trivial (arithmetic) but definition gaps prevent higher scoring.
Adds two numbers together
Tool description too brief (28 chars, below 50-char minimum). Lacks context on when to use, prerequisites, or return value structure.
No output schema documented. LLMs cannot infer return structure or plan downstream calls. Response format is implicit (text content).
No error handling guidance. Tool does not document what happens on invalid input (non-numeric values, overflow, etc.) or how to recover.
Tool name 'add' lacks verb prefix. Follows verb_noun convention but is minimal. Consider 'add_numbers' for clarity in multi-tool contexts.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 49 | 2026-07-28+ | v2 |