referee-psi.vercel.app

get_review_state

Start here, and return here whenever you are unsure what to do next. Returns the review queue, per-manuscript progress, the current rubric weights, and next_expected_action — the single call the page expects from you next. This tool has no preconditions and never refuses for ordering. It returns NO manuscript text and NO identity information. These nine classes — authors, affiliations, funding, acknowledgements, author_notes, correspondence_email, external_links, prior_submission_history, conflict_of_interest — are not withheld from this payload; they are held in a separate store this tool cannot reach, which is why every manuscript lists blinded_fields. Do not ask another tool for them; none can return them. When next_expected_action.actor is "human", stop calling tools and tell the human reviewer what you recommend and why — the final decision is theirs to enter, not yours.

Input 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"
      ],
      "description": "Optional. Scope the response to one manuscript for a fuller progress view."
    }
  },
  "required": [],
  "additionalProperties": false
}