Loading ToolBench
A remote MCP server providing calculator tools without authentication, deployed on Cloudflare Workers
Two tools with basic schemas and minimal descriptions. Both tools have input schemas with proper types (number, string, enum), but descriptions are extremely short (10-40 chars), falling well below the 50-200 char baseline for LLM-optimized descriptions. No output schemas documented. Error handling is minimal (divide-by-zero check in 'calculate' only). Tool names lack action verbs ('add' and 'calculate' are weak; 'perform_addition' and 'perform_calculation' would be clearer). No parameter descriptions beyond type hints. No composition guidance or chaining metadata.
Simple addition tool
Calculator tool with multiple operations
Tool descriptions are critically short (10-40 chars). 'Simple addition tool' and 'Calculator tool with multiple operations' lack context for LLM selection. Should explain WHAT the tool does, WHEN to use it, and what it returns (e.g., 'Adds two numbers and returns their sum as a text response').
Parameter descriptions are missing entirely. Zod schema defines types (z.number(), z.enum()) but LLMs cannot read JSON Schema, they rely on text descriptions. Each parameter needs a description explaining its role, range, and constraints.
Output schema is not documented. Tools return text responses but LLMs need to know the structure: is it always a number string? Can it be an error message? What fields are present? Document the response format explicitly.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 39 | 2026-07-28+ | v2 |
Tool names lack action verbs. 'add' and 'calculate' are weak; they don't clearly signal intent. Rename to 'perform_addition' or 'add_numbers' and 'perform_arithmetic' or 'calculate_result' to match verb_noun convention and improve LLM disambiguation.
Error handling is minimal. Only 'calculate' checks for divide-by-zero; 'add' has no validation. Error messages should guide recovery: 'Cannot divide by zero. Try a different divisor or use a different operation.' Include the invalid value and constraint violated.