Loading ToolBench
Example MCP server from Scalably. Replace this line.
Single tool with minimal definition quality. Tool name 'example_echo' lacks action verb clarity (should be 'echo_text'). Description is 67 chars, acceptable length but generic placeholder text ('Replace with real tools') signals this is a template, not production code. Input schema present with Zod validation but parameter description is minimal (11 chars: 'The text to echo'). No output schema documented. Error handling is basic (empty text check only). Tool annotations present (readOnlyHint=true) but insufficient for a real tool. This is intentionally a template; scoring reflects that it's not production-ready.
Return the text you pass in. Replace with real tools.
Tool name 'example_echo' does not start with a clear action verb. Should be 'echo_text' or 'return_text' to signal intent.
Description contains placeholder text ('Replace with real tools') indicating this is a template, not a production tool. Production descriptions must explain WHAT, WHEN, and WHY.
Output schema not documented. LLMs cannot plan downstream calls or extract fields without knowing the response structure.
Parameter description 'The text to echo' is only 11 characters. Should explain format, constraints, and use case (target: 50-150 chars).
Error handling only validates non-empty text. No guidance on what to do next, no categorization of error types (retryable vs user-fixable).
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | D | 50 | 2026-07-28+ | v2 |