Give it a URL, get a battle-tested E2E test suite. CLI + MCP server that explores, generates, runs, and fixes Playwright tests until all pass.
Critical gaps across all dimensions. Tool definitions lack input schemas entirely, cannot verify parameter types, constraints, or descriptions. No tool descriptions visible in registry or tool files. Tool names use generic verbs (explore, generate, run, fix) without clear object/action pairing. No output schemas documented. Error handling and recovery guidance absent. This server fails basic definition quality standards.
No input schemas visible for any tool. Cannot verify parameter types, constraints, or descriptions.
No tool descriptions present in registry or tool files. LLMs cannot determine when or why to select tools.
Tool names lack clear verb_noun structure. 'exploreTool', 'generateTool', 'runTool' are generic and do not convey specific actions. Should be 'explore_website', 'generate_test_suite', 'run_tests', etc.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 25 | 2026-07-28+ | v2 |
No output schemas documented. LLMs cannot plan downstream tool calls or extract required data. No pagination, result limits, or field documentation visible.
No error handling or recovery guidance visible. Tools do not indicate what to do on failure, whether errors are retryable, or how to self-correct.