Loading ToolBench
ModelContextProtocol server for checking domain availability and pricing via Vercel API
Single tool 'check-domain' has a basic schema (domain: string) but lacks critical quality markers. Description is present but generic (48 chars). No parameter description visible in schema. No output schema documented. No error handling guidance. Tool does one thing (domain availability check) but lacks LLM-optimization patterns. Naming is acceptable (verb_noun form) but descriptions fall short of production baseline (194 chars avg). No pagination, no structured output guidance, no recovery hints.
Checks if a domain is available and gets its price if available
Parameter 'domain' lacks description in schema. LLMs cannot infer whether to pass 'example.com', 'example', or a full URL.
No output schema documented. Tool returns text content but LLMs need to know the structure of success vs error responses to plan downstream actions.
Tool description (48 chars) is below production baseline (194 chars avg). Does not explain WHEN to use it, WHAT it returns, or prerequisites (Vercel API key requirement).
Error handling returns plain text without recovery guidance. 'Error checking domain: ...' gives LLM no actionable next step. Should indicate if error is retryable or user-fixable.
Inferred effective spec: <=2025-11-25.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | <=2025-11-25 | v2 |
API key passed as command-line argument (src/index.ts line 4) instead of environment variable injection. Credentials in process args risk exposure in logs and process listings.