Loading ToolBench
A simple calculator MCP server with basic arithmetic operations
Two tools with basic schemas and minimal descriptions. Both tools have input schemas with proper types (number, enum), but descriptions are extremely short (10-40 chars) and lack context for LLM selection. No output schema documentation. No error handling guidance. Tool names lack action verbs (add, calculate are weak; should be compute_sum, perform_arithmetic). No parameter descriptions beyond type hints. Schemas present but descriptions fall well below the 50-200 char baseline for A+ tools.
Simple addition tool
Calculator tool with multiple operations
Tool descriptions critically short (10-40 chars). 'Simple addition tool' and 'Calculator tool with multiple operations' lack context for LLM selection, when to use each tool, and what they return. Baseline is 50-200 chars.
Parameter descriptions missing entirely. Zod schema defines types (number, enum) but no descriptions for 'a', 'b', 'operation'. LLMs cannot infer parameter meaning from names alone.
No output schema documented. Tool responses return text content but LLMs have no formal schema to understand return structure, field names, or data types.
Tool names lack action verbs. 'add' and 'calculate' are weak; should be 'compute_sum' or 'perform_arithmetic' to signal intent clearly. Current names are ambiguous for LLM selection.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 52 | 2026-07-28+ | v2 |
Error handling minimal. Division by zero returns plain text error; no guidance for LLM on retry strategy, recovery steps, or error classification (retryable vs fatal).