Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: audit the provided GEO signals into scored findings and a 0-100 score, generate the site-update artefacts, and return the full report.
- analyze — Run pure deterministic GEO analysis over provided signals with no model call and return scored findings.
- compute_geo_score — Compute the overall 0-100 AI SEO and GEO score with its weighted rollup, returning the score alongside the findings behind it.
- build_artifacts — Generate the full site-update artefact set at once: robots.txt, sitemap.xml, llms.txt and suggested title and meta tags where the current ones need fixing.
- build_robots_txt — Generate a robots.txt that explicitly allows the AI crawlers — GPTBot, ClaudeBot, PerplexityBot and others — with a sitemap pointer.
- build_sitemap_xml — Generate a minimal sitemap.xml for the target.
- build_llms_txt — Generate an llms.txt following the llmstxt.org convention — a machine-readable site summary for AI agents.
- build_json_ld — Generate a schema.org JSON-LD skeleton — an Organization, WebSite and WebPage graph ready to paste into the head tag.
- suggest_meta_tags — Suggest a title and meta description, but only where the current one is missing or outside the ideal length band. A good tag is returned untouched.
- list_capabilities — List the agent's static capabilities: the available tools and the current GEO check set. Useful for discovery.
- plan_inputs — Plan the inputs for a tool: returns the clarifying questions, the JSON schema and a ready-to-edit example.
- discover_intent — Understand your goal and co-design the exact input through clarifying questions before running.
- open_form — Opens the guided form to collect the target site or page and the audit scope. The entry point for running the agent on your own data.
- run_form — Internal: invoked by the guided form when the user submits. Not for direct use.
