Loading ToolBench
MCP server with OAuth 2.0 authorization provider running on Cloudflare Workers, demonstrating remote authentication flows
Single tool 'add' has a basic schema with typed parameters but lacks depth. Description is minimal (18 chars, below 20-char threshold). No parameter descriptions provided, only type declarations. No output schema documented. No error handling guidance. No tool annotations. Naming is acceptable but generic. This server demonstrates minimal compliance with production tool patterns.
Adds two numbers together
Description too short (18 chars, below 20-char minimum). 'Adds two numbers together' provides no context for when/why to use this tool or what it returns.
Parameters lack descriptions. 'a' and 'b' have types (number) but no guidance on range, constraints, or expected values. LLMs cannot infer whether negative numbers, decimals, or very large values are valid.
Output schema not documented. Tool returns text content but no schema is visible describing the response structure, field names, or data types. Agents cannot plan downstream operations.
No error handling or recovery guidance. Tool provides no documentation of failure modes, invalid inputs, or how to recover from errors.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 40 | 2026-07-28+ | v2 |
No tool annotations. Tool lacks readOnlyHint, destructiveHint, or idempotentHint metadata to signal safety properties to agents.