cross-review

Ask Peers

ask_peers

Run a real API review round with selected AI peers; evidence is persisted and transported automatically. Get structured cross-review feedback and convergence verdicts without extra attachment steps.

Instructions

Run a real API review round against selected peers. AI evidence supplied in evidence is persisted durably and transported automatically; no separate attachment step is required. Runtime default uses real provider APIs; stubs run only when CROSS_REVIEW_STUB=1. 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

Name	Required	Description	Default
`task`	Yes
`draft`	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.
`session_id`	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.
`caller_status`	No		READY
`response_format`	No		json
`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.

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",
-  "draft"
-]New value: +[
+  "task",
+  "draft",
+  "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)."

Addedv4.4.12Aug 22, 2026
Removedv4.4.11Jul 17, 2026

Changed8 schema fields changedv4.4.9Jul 14, 2026

addedInput schema / properties / evidence

Added value: +{
+  "description": "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.",
+  "maxLength": 200000,
+  "type": "string"
+}

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

A4.1/5.0

Behavior4/5

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

Beyond annotations (which mark non-read-only, non-idempotent, open-world), the description adds evidence durability and automatic transport, provider-API runtime behavior, stub gating, and a capability-token requirement for existing sessions. This is meaningful context not inferable from annotations, though it leaves out cost and blocking behavior.

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

Conciseness5/5

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

Three sentences, each introducing a distinct facet: core action, evidence handling, and runtime/auth conditions. No filler; the most decision-relevant facts are front-loaded.

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 10-parameter tool with no output schema, the description gives the operational essentials (real vs stub, auth, evidence handling) but omits what the call returns, whether it blocks, and the semantics of required inputs like `task` and `draft`. The rich sibling set partially compensates, but an agent would still be guessing about the outcome and required content.

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?

Only 30% of parameters carry schema descriptions, so the description must compensate. It does clarify `evidence` (durable, SHA-256-addressed, auto-transported) and `session_id` (verified capability token needed), but leaves required `task`, `draft`, and `caller` without additional explanation; the coverage gap is only partially filled.

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

Purpose5/5

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

The description opens with a specific verb-resource pair ('Run a real API review round against selected peers'), names the exact input vector ('evidence') and how it is transported, and distinguishes the real-provider path from stubbed mode. This clearly separates it from session-management siblings.

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

Usage Guidelines4/5

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

It states when the real API path is used vs stubs ('stubs run only when CROSS_REVIEW_STUB=1') and explains the session auth condition, plus the implicit alternative to session_attach_evidence in the evidence parameter description ('attaches the same material out of band'). It does not explicitly name competing siblings like session_start_round or when to prefer them.

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

Ask Peers

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools