Skip to main content
Glama
LCV-Ideas-Software

cross-review

by LCV-Ideas-Software
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Start Until Unanimous

session_start_unanimous

Starts background cross-AI review rounds that run until unanimous agreement, a round cap, or budget limit, [persisting and sharing supplied evidence automatically].

Instructions

Start real API generation/revision rounds in the background until unanimity, max_rounds or budget limit. AI evidence supplied in evidence is persisted durably and transported automatically; no separate attachment step is required. v2.11.0: same caller + relator-lottery semantics as run_until_unanimous — see that tool for details. When session_id names an existing session, requires the verified capability token of that session's persisted petitioner; opening a new session does not.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeNoship
taskYes
peersNo
callerYes
evidenceNoRaw evidence from the authenticated AI caller. It is persisted automatically as durable, SHA-256-addressed caller_submitted_unverified material and transported to reviewers. This is the routine path; `session_attach_evidence` attaches the same material out of band and grants it no additional provenance.
lead_peerNo
max_roundsNoHard review-round ceiling when supplied, unless allow_auto_extension is explicitly true. Omit to use the existing runtime default for the selected mode.
session_idNo
max_cost_usdNo
review_focusNoOptional provider-neutral review scope anchor. This is not Claude Code's /focus UI command; it is injected as a front-loaded Review Focus prompt block for every selected peer, including OUT OF SCOPE handling for unrelated findings.
initial_draftNo
until_stoppedNo
response_formatNojson
allow_auto_extensionNoOpt in to at most two evidence-only auto-extensions. False keeps max_rounds rigid.
reasoning_effort_overridesNoOptional per-peer reasoning_effort overrides for this call. Keys are peer ids (codex|claude|gemini|deepseek|grok|perplexity); missing keys fall back to global config. This is a shared scale: adapters normalize unsupported literals to the selected model's documented enum (`ultra` becomes max on GPT-6 Astra, GPT-5.6, Kimi K3 via Perplexity and DeepSeek, and xhigh on Grok 4.6; older GPT-5 families use their own ceilings).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv4.4.22
    • removedInput schema / properties / max_rounds / default
      Removed value: -8
    • changedInput schema / properties / max_rounds / description
      Previous value: -"Hard review-round ceiling unless allow_auto_extension is explicitly true."New value: +"Hard review-round ceiling when supplied, unless allow_auto_extension is explicitly true. Omit to use the existing runtime default for the selected mode."
  2. Changed5 schema fields changedv4.4.18
    • removedInput schema / properties / caller / default
      Removed value: -"operator"
    • changedInput schema / properties / caller / enum
      Previous value: -[
-  "codex",
-  "claude",
-  "gemini",
-  "deepseek",
-  "grok",
-  "perplexity",
-  "operator"
-]New value: +[
+  "codex",
+  "claude",
+  "gemini",
+  "deepseek",
+  "grok",
+  "perplexity"
+]
    • changedInput schema / properties / evidence / description
      Previous value: -"Raw evidence from the authenticated AI caller. It is persisted automatically as durable, SHA-256-addressed caller_submitted_unverified material and transported to reviewers; no manual operator attachment is required. Do not call session_attach_evidence for this routine path."New value: +"Raw evidence from the authenticated AI caller. It is persisted automatically as durable, SHA-256-addressed caller_submitted_unverified material and transported to reviewers. This is the routine path; `session_attach_evidence` attaches the same material out of band and grants it no additional provenance."
    • changedInput schema / properties / reasoning_effort_overrides / description
      Previous value: -"Optional per-peer reasoning_effort overrides for this call. Keys are peer ids (codex|claude|gemini|deepseek|grok|perplexity); missing keys fall back to global config. This is a shared scale: adapters normalize unsupported literals to the selected model's documented enum (`ultra` becomes max on GPT-5.6, Kimi K3 via Perplexity and DeepSeek, and xhigh on Grok 4.6; older GPT-5 families use their own ceilings)."New value: +"Optional per-peer reasoning_effort overrides for this call. Keys are peer ids (codex|claude|gemini|deepseek|grok|perplexity); missing keys fall back to global config. This is a shared scale: adapters normalize unsupported literals to the selected model's documented enum (`ultra` becomes max on GPT-6 Astra, GPT-5.6, Kimi K3 via Perplexity and DeepSeek, and xhigh on Grok 4.6; older GPT-5 families use their own ceilings)."
    • changedInput schema / required
      Previous value: -[
-  "task"
-]New value: +[
+  "task",
+  "caller"
+]
  3. Changed1 schema field changedv4.4.13
    • changedInput schema / properties / reasoning_effort_overrides / description
      Previous value: -"Optional per-peer reasoning_effort overrides for this call. Keys are peer ids (codex|claude|gemini|deepseek|grok|perplexity); missing keys fall back to global config. This is a shared scale: adapters normalize unsupported literals to the selected model's documented enum (`ultra` becomes max on GPT-5.6 and high on Grok 4.5; older GPT-5 families use their own ceilings)."New value: +"Optional per-peer reasoning_effort overrides for this call. Keys are peer ids (codex|claude|gemini|deepseek|grok|perplexity); missing keys fall back to global config. This is a shared scale: adapters normalize unsupported literals to the selected model's documented enum (`ultra` becomes max on GPT-5.6, Kimi K3 via Perplexity and DeepSeek, and xhigh on Grok 4.6; older GPT-5 families use their own ceilings)."
  4. Changed10 schema fields changedv4.4.9
    • addedInput schema / properties / allow_auto_extension
      Added value: +{
+  "default": false,
+  "description": "Opt in to at most two evidence-only auto-extensions. False keeps max_rounds rigid.",
+  "type": "boolean"
+}
    • addedInput schema / properties / evidence / description
      Added value: +"Raw evidence from the authenticated AI caller. It is persisted automatically as durable, SHA-256-addressed caller_submitted_unverified material and transported to reviewers; no manual operator attachment is required. Do not call session_attach_evidence for this routine path."
    • addedInput schema / properties / max_rounds / description
      Added value: +"Hard review-round ceiling unless allow_auto_extension is explicitly true."
    • changedInput schema / properties / reasoning_effort_overrides / description
      Previous value: -"Optional per-peer reasoning_effort overrides for this call. Keys are peer ids (codex|claude|gemini|deepseek|grok|perplexity); missing keys fall back to global config. Useful to dial down expensive peers (e.g. Grok grok-4.20-multi-agent xhigh = 16 agents, or Perplexity sonar-deep-research that bills citation + reasoning + search queries separately) for routine reviews without editing the host MCP configs."New value: +"Optional per-peer reasoning_effort overrides for this call. Keys are peer ids (codex|claude|gemini|deepseek|grok|perplexity); missing keys fall back to global config. This is a shared scale: adapters normalize unsupported literals to the selected model's documented enum (`ultra` becomes max on GPT-5.6 and high on Grok 4.5; older GPT-5 families use their own ceilings)."
    • changedInput schema / properties / reasoning_effort_overrides / properties / claude / enum
      Previous value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]New value: +[
+  "none",
+  "minimal",
+  "low",
+  "medium",
+  "high",
+  "xhigh",
+  "max",
+  "ultra"
+]
    • changedInput schema / properties / reasoning_effort_overrides / properties / codex / enum
      Previous value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]New value: +[
+  "none",
+  "minimal",
+  "low",
+  "medium",
+  "high",
+  "xhigh",
+  "max",
+  "ultra"
+]
    • changedInput schema / properties / reasoning_effort_overrides / properties / deepseek / enum
      Previous value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]New value: +[
+  "none",
+  "minimal",
+  "low",
+  "medium",
+  "high",
+  "xhigh",
+  "max",
+  "ultra"
+]
    • changedInput schema / properties / reasoning_effort_overrides / properties / gemini / enum
      Previous value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]New value: +[
+  "none",
+  "minimal",
+  "low",
+  "medium",
+  "high",
+  "xhigh",
+  "max",
+  "ultra"
+]
    • changedInput schema / properties / reasoning_effort_overrides / properties / grok / enum
      Previous value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]New value: +[
+  "none",
+  "minimal",
+  "low",
+  "medium",
+  "high",
+  "xhigh",
+  "max",
+  "ultra"
+]
    • changedInput schema / properties / reasoning_effort_overrides / properties / perplexity / enum
      Previous value: -[
-  "none",
-  "minimal",
-  "low",
-  "medium",
-  "high",
-  "xhigh",
-  "max"
-]New value: +[
+  "none",
+  "minimal",
+  "low",
+  "medium",
+  "high",
+  "xhigh",
+  "max",
+  "ultra"
+]
  5. First observedv4.4.8

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the write/safety profile (readOnlyHint=false, idempotentHint=false, destructiveHint=false, openWorldHint=true), so the bar is lower. The description still adds real behavioral context: background execution, durable SHA-256-addressed persistence of evidence, the 'no separate attachment step' guarantee, and the verified capability-token requirement when session_id names an existing session. It does not describe completion/polling behavior, which is a minor gap.

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

Conciseness4/5

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

Four sentences, front-loaded with the core action and termination conditions. Each sentence carries distinct information (behavior, evidence path, sibling reference, session_id auth). Slightly dense but no filler.

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

Completeness3/5

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

For a 15-parameter orchestration tool with no output schema, nested objects, and heavy sibling overlap, the description is thin. It covers the evidence path and auth requirement but leaves the mode enum, cost/round controls, and how the caller learns the outcome (polling via session_poll) to inference. Adequate but incomplete.

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 description coverage is low (33%) across 15 parameters, so the description must compensate. It does explain evidence persistence/transport and the session_id capability-token semantics, and references caller semantics via run_until_unanimous. But mode, task, peers, lead_peer, max_cost_usd, initial_draft, until_stopped, and response_format receive no meaning from either source.

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?

States a specific verb and resource: 'Start real API generation/revision rounds in the background until unanimity, max_rounds or budget limit.' The scope and termination conditions are clear. However, it defers differentiation from the sibling run_until_unanimous ('same semantics — see that tool for details') rather than explaining how this tool differs from it, so an agent cannot cleanly choose between the two from this text alone.

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

Usage Guidelines3/5

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

Gives implied usage context: evidence is persisted automatically so no separate attach step is needed, and the capability-token requirement is stated for the existing-session case. But there is no explicit when-to-use vs run_until_unanimous or session_start_round, and no exclusions or prerequisites beyond the session_id note.

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

Deploy Server

Other Tools