Skip to main content
Glama
LCV-Ideas-Software

cross-review

by LCV-Ideas-Software
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Remote

Start Review Round

session_start_round

Start a background peer-review round and get a job ID for polling; evidence is durably persisted and automatically sent to reviewers, with no separate attachment step.

Instructions

Start a real peer-review round in the background and return immediately with a session_id/job_id for polling. AI evidence supplied in evidence is persisted durably and transported automatically; no separate attachment step is required. 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
taskYes
draftYes
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.
session_idNo
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.
caller_statusNoREADY
response_formatNojson
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. 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",
-  "draft"
-]New value: +[
+  "task",
+  "draft",
+  "caller"
+]
  2. 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)."
  3. Changed8 schema fields changedv4.4.9
    • 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"
+]
  4. First observedv4.4.8

TDQS

A4.2/5.0
Behavior4/5

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

The description adds meaningful behavior beyond annotations: the operation is asynchronous, returns immediately, persists evidence durably, transports it automatically, and imposes capability-token requirements when resuming an existing session. Annotations only convey readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false; the description enriches that with execution and authentication context.

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?

The description is three dense, front-loaded sentences with no filler. The core action and return behavior appear first, followed by evidence handling and the session capability caveat. Every sentence earns its place and no information is repeated from the schema.

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 complex async tool with 10 parameters and no output schema, the description covers the key operational essentials: it starts a background round, returns a pollable ID, persists evidence, and clarifies auth requirements. It does not explain the polling lifecycle or the meaning of task/draft/caller beyond their names, and without an output schema some return-format detail is left unspecified, but the description is still reasonably complete for selecting and invoking the tool correctly.

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 at 30%, so the description must compensate for many parameters. It does add meaning for `evidence` (durable persistence, automatic transport) and `session_id` (capability-token requirement), which are genuinely helpful. However, the other seven parameters — task, draft, caller, peers, caller_status, response_format, and reasoning_effort_overrides — receive no additional semantic clarification in the main description, leaving gaps for a low-coverage schema.

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 states a specific verb and resource: "Start a real peer-review round in the background and return immediately with a session_id/job_id for polling." This clearly distinguishes the tool from read-oriented siblings like session_read or session_poll, and from the related start_unanimous tool by emphasizing a background, pollable round.

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?

The description gives concrete usage context: it positions itself as the routine path by saying evidence is "transported automatically; no separate attachment step is required," implicitly routing away from session_attach_evidence. It also clarifies the existing-session condition: opening a new session does not require the petitioner's capability token, while resuming does. It does not explicitly compare against alternatives like ask_peers or session_start_unanimous, so it falls just short of a 5.

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