cross-review

Run Until Unanimous

run_until_unanimous

Generate or revise a draft, then run API peer-review rounds until reviewers unanimously return READY or the configured max_rounds is reached.

Instructions

Generate or revise a draft and continue real API peer-review rounds until unanimous READY or the configured max_rounds is reached. AI evidence supplied in evidence is persisted durably and transported automatically; no separate attachment step is required. v2.11.0: when caller is set to a peer id (claude|codex|gemini|deepseek|grok|perplexity), the relator lottery activates: omit lead_peer to have the server randomly select a non-caller peer as relator (modeled on judicial panels), or supply an explicit lead_peer that is NOT the caller. An explicit lead_peer === caller is rejected at the server with caller_cannot_be_lead_peer — an agent never reviews itself (workspace HARD GATE).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`mode`	No		ship
`task`	Yes
`peers`	No
`caller`	Yes
`evidence`	No	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.
`lead_peer`	No
`max_rounds`	No	Hard review-round ceiling when supplied, unless allow_auto_extension is explicitly true. Omit to use the existing runtime default for the selected mode.
`max_cost_usd`	No
`review_focus`	No	Optional 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_draft`	No
`until_stopped`	No
`response_format`	No		json
`allow_auto_extension`	No	Opt in to at most two evidence-only auto-extensions. False keeps max_rounds rigid.
`reasoning_effort_overrides`	No	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).

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv4.4.22Oct 5, 2026

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."

Changed5 schema fields changedv4.4.18Sep 17, 2026

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"
+]

Changed1 schema field changedv4.4.13Aug 26, 2026

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)."

Changed10 schema fields changedv4.4.9Jul 14, 2026

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"
+]

First observedv4.4.8Jul 4, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already declare mutating, non-idempotent, open-world, non-destructive behavior. The description adds real value beyond them: durable SHA-256-addressed persistence and automatic transport of evidence, the server-side rejection with error code caller_cannot_be_lead_peer, max_rounds acting as a hard ceiling unless auto-extension is opted in, and the relator-lottery mechanics. It omits cost/rate implications despite exposing max_cost_usd.

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?

The first sentence front-loads the core behavior cleanly, and the following sentences are information-dense rather than padded. Some changelog framing ('v2.11.0:', 'workspace HARD GATE') is slightly noisy but each clause carries substantive rules.

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 14-parameter orchestration tool with no output schema and low schema coverage, the description covers the highest-risk mechanics (self-review gate, evidence handling) but leaves a majority of parameters and the overall mode semantics unexplained. Adequate but with clear gaps for such a complex tool.

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 (36%), so the description must compensate. It meaningfully explains caller/lead_peer interaction, the evidence lifecycle, and the auto-extension behavior, but leaves mode, peers, max_cost_usd, initial_draft, until_stopped, and response_format entirely unexplained in both schema and description.

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 specific verbs and resources: 'Generate or revise a draft and continue real API peer-review rounds until unanimous READY or max_rounds.' It also implicitly distances itself from session_attach_evidence by saying no separate attachment step is needed. It does not, however, explicitly differentiate itself from close siblings like session_start_unanimous or session_start_round.

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?

It gives behavioral conditions for the caller/lead_peer combinations (omit lead_peer for lottery, or supply a non-caller peer), and clarifies that the evidence path is routine versus session_attach_evidence. But it never states when to choose this tool over the many sibling session/round tools, so the agent must infer the routing.

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

Run Until Unanimous

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools