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 are action-oriented (add, calculate) but descriptions don't explain WHEN to use each tool or their differences. No parameter descriptions beyond type hints in schema. Lacks guidance on tool composition or error recovery.
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. No explanation of when to use add vs calculate, prerequisites, or return format.
Input parameters lack descriptions. Schema shows types (a: number, b: number, operation: enum) but no parameter-level descriptions explaining what each controls or valid ranges. LLMs cannot infer meaning from names alone.
No output schema documented. Tool responses return text content but LLMs don't know the structure, field names, or how to chain results to downstream tools. Breaks tool composition patterns.
Minimal error handling. Only divide-by-zero check in calculate tool; add tool has no validation. No guidance on retryability, user-fixable errors, or recovery steps. Error responses are plain text without actionable next steps.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 44 | 2026-07-28+ | v2 |
Tool naming ambiguity. Both 'add' and 'calculate' can perform addition. No clear distinction in names or descriptions. LLM must reason about which to call, wasting tokens and risking wrong selection.