Tools provided
Tools the agent exposes — your AI client calls them automatically when it needs them.
- run_full — Orchestrated path: score a provided debt-signal batch end-to-end — interest rate per file, hotspot list, capacity-bounded quarterly payment plan and draft Jira epics — with the scoring model echoed back in the result.
- analyze — Run pure deterministic scoring over a provided debt batch with no model call and return scored per-file findings, worst first.
- score_items — Score each file's interest rate, weighted score and severity tier from its raw signals — the scoring step on its own.
- hotspot_files — Return the top-scoring files from a provided batch — where to look first.
- build_quarterly_plan — Pack the scored debt into a first-fit, capacity-bounded quarterly payment plan starting from the batch's quarter, and report what did not fit rather than dropping it silently.
- build_jira_epics — Build draft Jira epics for the highest-priority debt items. Drafts only — nothing is created live.
- list_capabilities — List the agent's static capabilities: the available tools and the full scoring model — weights, normalisation caps and tier 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 debt-signal batch, the repository label and the target quarter. 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.
