Skip to main content
Glama

start_ultraplan

Orchestrate a multi-agent planning session: collect specialist input, review and revise drafts, then secure sign-offs before finalizing the plan.

Instructions

Plan with specialist agents: you (the orchestrator) own and write the plan; agents give input before the draft, review each version, then sign off. With no draft_plan, returns input and awaiting_plan: write v1 with contributor tags such as [cfo], then call submit_plan. With draft_plan, reviews it as v1 and returns awaiting_revision. Revise in response to amendments, explaining rejected advice; call submit_plan with final: true to collect sign-offs and close. Alternatively set planner to a persona to draft/revise/sign off server-side in one call. If that run returns a step with error, the session remains open. A step with phase: "plan" returns the unreviewed latest version and previousReviews when an earlier version was reviewed. Continue with submit_plan: omit plan to review or sign off that version as-is, or pass a full revised plan; or close with end_ultraplan. Show the final document to the user verbatim, including every agent's input and sign-off. The final result ends with a JSON trailer {ultraplan_id, archived, tally}; signed off means no OBJECT and no UNCLEAR sign-off. With execution_ready: true, plans end with a roundtable-tasks block and sign-offs check it, so propose_contract { from_session: ultraplan_id } can build a contract from it. Public runs post the task and phase outputs, never context.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "agents": "<agents>",
      "task": "<task>"
    },
    "name": "start_ultraplan"
  }
}

Input Schema

NameRequiredDescriptionDefault
duelNoOptional duel id (duel-...) from ROUNDTABLE_HOME/duels to make the focus of this session: a scrubbed, size-capped brief of the duel (teams, artifacts, verdicts, tally, dissents) is added to the context every participant sees, as untrusted content to discuss. An unknown or invalid id is an error before any provider call.
taskYesWhat the plan must accomplish; required and non-empty.
modelNoModel id. Defaults: claude-sonnet-5-5 (anthropic), gpt-5.6-luna (openai), zai-org/GLM-5.3 (together), qwen/qwen3-235b-a22b-instruct-2507 (replicate), qwen3:14b (ollama), default (openai_compatible). Model aliases: "opus" (claude-opus-5-5), "sonnet" (claude-sonnet-5-5), "haiku" (claude-haiku-5-5). Replicate accepts owner/name, owner/name:version, or a https://replicate.com/owner/name URL.
agentsYesSpecialists contributing input, independent reviews and sign-offs. A planner may also be a participant.
publicNoDefault false. Only set true when the human explicitly asks for a public session. When true, the whole session is posted live to the configured public channel and is world-readable: the topic/agenda, every agent reply, every message you send with say/nudge, and the summary. The context argument is never posted, but agents may paraphrase it in their replies, so keep context generic. Never include personal information, credentials, or private code anywhere in a public session. The result includes public.url so the human can watch live.
contextNoOptional background shared with the agents; never posted publicly.
plannerNoOptional persona that owns drafting and revision server-side; runs the whole loop in one call.
base_urlNoOnly with provider "openai_compatible": base URL of an OpenAI-compatible /v1 endpoint (e.g. http://localhost:1234/v1). Overrides OPENAI_COMPATIBLE_BASE_URL. OPENAI_COMPATIBLE_API_KEY, if set, is sent only to the OPENAI_COMPATIBLE_BASE_URL origin or one listed in ROUNDTABLE_OPENAI_COMPATIBLE_TRUSTED_ORIGINS; any other base URL gets no Authorization header and must be https (http only to loopback, or to private addresses with ROUNDTABLE_ALLOW_PRIVATE_BASE_URLS=1), never a cloud metadata or (without that setting) private address.
providerNoLLM provider. Omit or use auto for provider judgment (the router picks a healthy provider per seat and reports why in a routing block); otherwise the chosen provider is used as given. Options: auto; anthropic; openai; together (Together AI — any Together model id, e.g. zai-org/GLM-5.3 or Qwen/...); replicate (owner/name, owner/name:version, or https://replicate.com/owner/name); ollama (local, only when reachable); openai_compatible (any /v1/chat/completions server — set OPENAI_COMPATIBLE_BASE_URL or pass base_url).
repo_dirNoA directory inside the repository the plan is for. When earlier postmortems of that project left lessons, a bounded "Lessons from past postmortems" section (misreadings first) is added to the context the agents plan with. Never posted publicly.
connectorsNoOptional names of configured MCP connectors (roundtable config set connector) that every seat may call as tools during its turn. Only read-only tools are offered unless the connector's config lists more; tool results are untrusted data and are scrubbed. Seats on providers without tool support (Replicate) speak without them. An unknown connector is an error before any provider call.
draft_planNoOptional full draft: becomes v1 by orchestrator and skips the input phase. Whitespace-only counts as absent.
duel_sourceNoDefault true; only with duel. The duel brief is resent on every turn to every participant (a full brief can be about 20k tokens per turn). Set false to leave out artifact file contents and keep titles, file names and sizes, verdicts, tally and dissents.
execution_readyNoDefault false. True when the plan will be executed heads-down: planner drafts and revisions (and your next steps) must end with a fenced roundtable-tasks JSON block of tasks, commands and interfaces, and sign-offs check it.
revision_roundsNoPlanner only: review/revise cycles before sign-off, default 1, clamped to 1..3.
seat_connectorsNoOptional per-seat limits, used with connectors: a map from a seat (agent) name to the subset of connectors that seat may call, e.g. {"ada": ["figma"], "bob": ["jira"]}. A seat not listed gets all of the session's connectors; an empty list gives that seat none. Every connector named must also be in connectors, and every seat must be at the table; otherwise the call fails before anything starts.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv2.0.0

TDQS

A4/5.0
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations cover open-world, non-read-only, non-idempotent, so the description's added value is the failure and exposure semantics: a step with error leaves the session open, public runs post task and phase output but never context, and the result ends with a {ultraplan_id, archived, tally} trailer. It does not disclose the cost/latency profile of fanning out to multiple providers, nor what happens if the tool is called again with the same arguments despite idempotentHint=false.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The core concept and the no-draft-with-draft branch are front-loaded, which is right. But the remainder is one dense paragraph packing return values, revision semantics, planner delegation, error handling, the review-only path, an output-format instruction, and the contract hookup, with no separation between the main flow and edge cases.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a sixteen-parameter, multi-phase orchestration tool with no output schema, the description carries the necessary burden: it explains the awaited states, what a returned plan step gives you, the JSON trailer, and the sign-off definition. Missing pieces are mostly operational (cost, latency, and what calling it twice does), not correctness-critical.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so parameters are already documented in depth, and the description largely restates draft_plan, planner, and execution_ready rather than extending them. It does add workflow meaning the schema lacks: what draft_plan skips, what planner does across the whole loop, and why execution_ready implies a roundtable-tasks block that sign-offs check. That is genuine added value, but it covers only a few of the sixteen parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The opening sentence states the resource and the model clearly: an orchestrated planning session with specialist agents where the caller owns the plan and agents give input, review, and sign off. It distinguishes itself from the follow-on tools by naming submit_plan and end_ultraplan explicitly. It never says the tool *starts* a session in so many words, but the phase language (input -> draft -> review -> sign-off) makes the initiating role unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Offers explicit branching: no draft_plan means you write v1 and call submit_plan, with draft_plan means it is reviewed as v1 and you revise; setting planner delegates the whole loop server-side; end_ultraplan closes the session. The execution_ready flag is tied to a concrete downstream action (propose_contract with from_session). Almost no routing decision is left to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.