Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: score provided GEO scan data against the versioned ruleset, narrate how to fix each gap, and return the findings together with a deterministic fix-PR proposal.
- analyze — Run pure deterministic analysis over provided GEO scan data with no model call and return scored findings, worst first.
- compliance_score — Compute the overall GEO compliance score from 0 to 1, reported alongside its coverage — which ruleset rules were measured, which were not, and which supplied keys fall outside the ruleset.
- propose_fix_pr — Build the deterministic fix-PR proposal — title, branch, description and the files to change — from the non-compliant findings. No model call and no GitHub write.
- list_capabilities — List the agent's static capabilities: the available tools, the versioned GEO ruleset and each rule's warning and critical thresholds. 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 and scan 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.
