2026-06-23T13:16:00

{
  "catalogue_size": 8,
  "loaded": [],
  "results": [
    {
      "name": "start_project",
      "description": "THE ENTRY POINT. Create a project + seed its research plan (methodology -> analyze/act/verify\n        scaffolding; none -> one dischargeable root frame task); the goal is the How-Might-We.\n        MANDATORY NEXT: start_run(project_id), then loop run_step(run_id) until kind=='done' — councils,\n        syntheses and hypotheses MUST be produced THROUGH that loop (run_step dispatches each step), NOT\n        by calling record_* directly: only inside the loop do the plan gates and assess_project stay\n        honest (a project recorded past the loop reads as 0 evidence / 'stalled' and won't close). Read\n        the `sonaloop://guide/research` resource for the full canonical path. (Personas should exist\n        first — see list_personas; a thin cohort pulls from the 300+-persona catalog via\n        catalog_search/catalog_recommend → catalog_pull.)",
      "parameter_keys": [
        "description",
        "goal",
        "icon",
        "methodology",
        "persona_ids",
        "title"
      ],
      "loaded": false
    },
    {
      "name": "brief_council",
      "description": "Gather a council. A council is scoped to a research project, so `project_id` is\n        REQUIRED (create one first with create_research_project; personas are global and need\n        no project). Without persona_ids: returns candidate personas to select from. With\n        persona_ids: returns each participant's loaded agent context (SOUL + memory) to author\n        turns against. Pass `artifact_ids` (or omit to include every project artifact) to ground\n        the council in the CAPTURED artifact(s) — a URL/website, a prototype link, or A/B variants\n        present side-by-side. Then author proposal/votes/exec_summary and call record_council. See\n        the run-council skill.",
      "parameter_keys": [
        "artifact_ids",
        "context",
        "count",
        "filters",
        "persona_ids",
        "project_id",
        "prompt"
      ],
      "loaded": false
    },
    {
      "name": "list_personas",
      "description": "Lean one-line overview of personas (slug/name/age/role/segment) — drill in with\n        get_persona for the full profile. Pass compact=False for full profiles (large).\n        Paginated per the shared convention (docs/pagination.md): `limit` (default 25) +\n        opaque `cursor` over a stable name/slug sort; answers {items, total, has_more,\n        next_cursor} — `total` counts the whole filtered set, `next_cursor` is present\n        exactly when has_more. A cursor only fits the filter set it was issued under;\n        no params → the first page (backward compatible).",
      "parameter_keys": [
        "compact",
        "cursor",
        "filters",
        "limit"
      ],
      "loaded": false
    },
    {
      "name": "query_personas",
      "description": "Paginated lean persona rows, filterable by free text. Stable ordering + next_offset.",
      "parameter_keys": [
        "limit",
        "offset",
        "q"
      ],
      "loaded": false
    },
    {
      "name": "record_council",
      "description": "Persist a host-authored council. Shape it by what you pass (the UI derives the mode):\n        DISCOVERY = `questions` (open user-research questions), NO proposal/votes; EVALUATION =\n        `proposal` (a concept reacted to) + stances; DECISION = `proposal` + `votes`.\n\n        Author the voices as `statements` (the ONE voice primitive): one per persona utterance —\n        {persona_id, text, stance:{value -2..2, label?: support|conditional|neutral|skeptical|oppose}\n        (the closed scale — see suggest_stances), about:{kind:'prompt', id:'q0'|'proposal'},\n        refs:[{kind,id,anchor,role}|{kind:'memory',text}]}. For a DISCOVERY council set each\n        statement's about.id to the question it answers ('q0','q1',…) so the page renders a moderated\n        Q→A transcript. `findings` is the optional analysis ({text, kind, score, refs}); `prompts` are\n        derived from questions/proposal when omitted. A council MUST belong to a research project.\n        Pass a stable `key` for a deterministic id (idempotent upsert → resumable runs).",
      "parameter_keys": [
        "exec_summary",
        "findings",
        "key",
        "persona_ids",
        "project_id",
        "prompt",
        "prompts",
        "proposal",
        "questions",
        "selection_reason",
        "statements",
        "summary"
      ],
      "loaded": false
    },
    {
      "name": "add_artifact",
      "description": "Bring a REAL artifact into a project's council pool so personas react to what is ACTUALLY\n        there — a live URL/website, a prototype link (kind='prototype', e.g. Figma), or one side of an\n        A/B comparison (kind='variant'). The page is CAPTURED to a grounded text snapshot (title,\n        meta, headings, visible copy) + a captured-at timestamp + content hash, so the run is\n        reproducible. Capture degrades gracefully (a dead link still stores the ref). Add TWO+ variants\n        to compare them in one council (the head_to_head plumbing). Then run brief_council with\n        artifact_ids=[...] (or omit it to include all). Pass `capture=False` to store the ref only.",
      "parameter_keys": [
        "capture",
        "key",
        "kind",
        "label",
        "project_id",
        "title",
        "url"
      ],
      "loaded": false
    }
  ],
  "next": "Call mcp_describe_tool for details or mcp_load_tools to make selected tools callable."
}

{
  "loaded": [
    "add_artifact",
    "brief_council",
    "list_personas",
    "query_personas",
    "record_council",
    "start_project"
  ],
  "unavailable": [],
  "active_tools": [
    "mcp_search_tools",
    "mcp_describe_tool",
    "mcp_load_tools",
    "mcp_search_playbooks",
    "mcp_read_playbook",
    "list_personas",
    "query_personas",
    "start_project",
    "brief_council",
    "record_council",
    "add_artifact"
  ],
  "note": "Loaded tool schemas are available from the next model step onward."
}

{
  "ok": true,
  "data": {
    "items": [
      {
        "id": "persona_315f93c315594940",
        "slug": "mira-schulz",
        "display_name": "Mira Schulz",
        "url": "http://127.0.0.1:8787/personas/persona_315f93c315594940",
        "age_range": "30-39",
        "role": "HR business partner",
        "segment": "Germany"
      },
      {
        "id": "persona_2142627145e123cb",
        "slug": "nina-vogt",
        "display_name": "Nina Vogt",
        "url": "http://127.0.0.1:8787/personas/persona_2142627145e123cb",
        "age_range": "35-44",
        "role": "Head of Operations",
        "segment": "Germany"
      },
      {
        "id": "persona_b929d201035e29c9",
        "slug": "oskar-lehmann",
        "display_name": "Oskar Lehmann",
        "url": "http://127.0.0.1:8787/personas/persona_b929d201035e29c9",
        "age_range": "45-54",
        "role": "Finance controller",
        "segment": "Germany"
      },
      {
        "id": "persona_138ee595cd23234c",
        "slug": "tarek-demir",
        "display_name": "Tarek Demir",
        "url": "http://127.0.0.1:8787/personas/persona_138ee595cd23234c",
        "age_range": "40-49",
        "role": "Warehouse shift lead",
        "segment": "Germany"
      }
    ],
    "total": 4,
    "has_more": false
  },
  "next_recommended_tool": {
    "name": "catalog_search",
    "reason": "cohort thin or empty? browse 300+ ready-made catalog personas before authoring new ones"
  },
  "_meta": {
    "tool": "list_personas",
    "latency_ms": 5.5,
    "server_version": "0.2.0",
    "schema_version": 4
  }
}