Robot Speed MCP exposes 3 tools with minimal schema documentation. All tools have basic descriptions (15-30 chars), but lack parameter descriptions, output schemas, and error handling guidance. Input schemas are present but incomplete, parameters have types but no descriptions. No tool annotations, no pagination support, no recovery guidance. This is a bare-bones integration that would require significant hardening for production use.
Full 8-category SEO audit
Keyword suggestions
Quick SEO score (0-100)
All tool descriptions are under 30 characters and lack context for LLM selection. 'Full 8-category SEO audit' does not explain when to use audit vs score, what it returns, or prerequisites.
No parameter descriptions provided. The 'url' parameter in audit and score lacks guidance on format, length, or valid schemes. The 'topic' parameter in keywords has no constraints or examples.
Output schemas are not documented. LLMs cannot plan downstream actions or extract results without knowing what fields audit, score, and keywords return.
No error handling or recovery guidance. If a URL is invalid or a topic yields no results, the LLM has no actionable error message or fallback strategy.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 37 | 2026-07-28+ | v2 |
Tool names lack action verbs. 'audit', 'score', and 'keywords' are nouns or ambiguous verbs. Clearer names like 'analyze_seo_audit', 'get_seo_score', 'suggest_keywords' would improve LLM intent inference.