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) and lack context for LLM selection. No output schema documentation. Error handling is minimal (divide-by-zero check in calculate tool only). Tool names lack action verbs (add, calculate are weak; should be compute_sum, perform_arithmetic). No parameter descriptions beyond type hints. Schemas are present but descriptions fall well below the 50-200 char baseline for A-grade 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 when/why to use each tool. LLMs cannot distinguish between add and calculate without longer, intent-focused descriptions.
Tool names lack action verbs. 'add' and 'calculate' are generic; should be 'compute_sum' or 'perform_arithmetic' to signal intent clearly. Current names do not follow verb_noun convention.
No parameter descriptions. Schema defines types (a: number, b: number, operation: enum) but provides no descriptions explaining what each parameter controls or its valid range/format.
Output schema not documented. Tools return text content but no schema is declared for the response structure. LLMs cannot plan downstream operations without knowing response fields.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 38 | 2026-07-28+ | v2 |
Minimal error handling. Only divide-by-zero check in calculate tool; add tool has no validation. No recovery guidance or error classification (retryable vs fatal).