GEO and AEO artifacts for answer engines and agents. Provides tools for auditing sites, generating llms.txt, and creating JSON-LD structured data.
Three tools with basic schemas and descriptions, but significant gaps in parameter documentation and output schema clarity. Tool names lack action verbs (auditUrl, genLlms, genJsonLd use camelCase instead of verb_noun convention). Descriptions are present but brief (10-80 chars, below the 50-200 char LLM-optimized baseline). Parameter descriptions exist for siteFacts object but lack detail on constraints, formats, and expected values. No visible output schema documentation. Error handling and recovery guidance absent. Schema definitions are minimal, only required fields and basic types shown, no examples or validation rules.
Score any live URL 0–100 for SEO, GEO, and AEO.
Generate JSON-LD schema.org structured data.
Generate llms.txt - a short site map for AI answer engines.
Tool names do not follow verb_noun convention. 'auditUrl', 'genLlms', 'genJsonLd' use camelCase and lack clear action verbs. Should be 'audit_url', 'generate_llms_txt', 'generate_json_ld' to match LLM parsing expectations.
No output schema documented for any tool. LLMs cannot plan downstream calls or extract results without knowing return structure. auditUrl should document score fields (seo, geo, aeo scores); genLlms/genJsonLd should document generated content structure.
Parameter descriptions lack constraint details. 'siteName', 'siteUrl', 'description' have minimal guidance on format, length, or validation rules. Missing: URL format requirements, name length limits, description character limits.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 41 | 2026-07-28+ | v2 |
Tool descriptions are too brief (10-80 chars vs 50-200 char baseline). 'Score any live URL 0 - 100 for SEO, GEO, and AEO' lacks context on when to use this vs alternatives, what prerequisites exist, and what the scores mean.
No error handling or recovery guidance. If auditUrl fails on an invalid URL, or genJsonLd receives an unsupported 'kind' value, no actionable error message guides the LLM to retry or correct input.