referee-psi.vercel.app
A double-blind peer-review room where the page is the boundary between a browser AI agent and untrusted manuscript text. All manuscripts are fictional.
First seen 2026-11-05 · Last seen 2026-11-05 · Source: webmcp.com
Answer 3 · Act 3 · Transact 1 · Score: Not yet scored
Tool inspector
submit_recommendation
Do not call this expecting it to work. The final recommendation on a manuscript is the human reviewer's decision and cannot be made through the tool layer — this call always returns REQUIRES_HUMAN, and the attempt is recorded in the review ledger. It exists so the boundary is visible rather than implicit. What to do instead: when get_review_state reports next_expected_action.actor as "human", stop calling tools and write the human a short summary — your recommendation, the criterion scores, and the evidence-backed findings behind each. The human enters the decision in the page. If you call this anyway, put your intended recommendation in the arguments; the refusal hands it back to the human as a proposal for them to accept, change, or ignore.
Input schema
| Property | Type | Required | Description |
|---|---|---|---|
manuscript_id |
string | yes | — |
recommendation |
string | yes | — |
rationale |
string | yes | Your reasoning, grounded in findings you already asserted. |
confidence |
string | no | — |
Raw JSON schema
{
"type": "object",
"properties": {
"manuscript_id": {
"type": "string",
"enum": [
"MS-101",
"MS-102",
"MS-103",
"MS-104",
"MS-105",
"MS-106",
"MS-107",
"MS-108",
"MS-109",
"MS-110",
"MS-111",
"MS-112"
]
},
"recommendation": {
"type": "string",
"enum": [
"accept",
"minor_revision",
"major_revision",
"reject"
]
},
"rationale": {
"type": "string",
"minLength": 30,
"maxLength": 2000,
"description": "Your reasoning, grounded in findings you already asserted."
},
"confidence": {
"type": "string",
"enum": [
"low",
"medium",
"high"
]
}
},
"required": [
"manuscript_id",
"recommendation",
"rationale"
],
"additionalProperties": false
}
Similar websites
pocketgull.app
Pocket Gull is a real-time clinical AI consult engine powered by Google Gemini. Features 10D multi-paradigm strategy, FHIR R4 export & 3D spatial anatomy.
webmcp-six-lac.vercel.app
AI Navigation Layer: Model Context Protocol (MCP) Semantic DOM integration for intelligent, safe, and observable web navigation.
ghqsandbox.net
Interactive math and physics tools an AI agent can drive directly through WebMCP.
app.formative.com
Formative classroom assessment and learning platform