Skip to main content
Glama

message_reviewer

Send private messages to specific reviewers about paper submissions, with preview capability before final confirmation.

Instructions

Send a private message to a specific reviewer. Visible to the reviewer, ACs, SACs, and PCs.

Returns a preview — call confirm_submission to actually send it.

Args: venue_id: The venue identifier. submission_number: The paper number. reviewer_id: The reviewer's anonymous ID (e.g., 'Reviewer_ABCD'). subject: Message subject line. message_text: Message body.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
venue_idYes
submission_numberYes
reviewer_idYes
subjectYes
message_textYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The message_reviewer tool handler is defined here. It constructs a message payload for a specific reviewer on an OpenReview submission and adds it to the pending store for confirmation.
    async def message_reviewer(
        venue_id: str,
        submission_number: int,
        reviewer_id: str,
        subject: str,
        message_text: str,
    ) -> str:
        """Send a private message to a specific reviewer. Visible to the reviewer, ACs, SACs, and PCs.
    
        Returns a preview — call confirm_submission to actually send it.
    
        Args:
            venue_id: The venue identifier.
            submission_number: The paper number.
            reviewer_id: The reviewer's anonymous ID (e.g., 'Reviewer_ABCD').
            subject: Message subject line.
            message_text: Message body.
        """
        client = get_client()
        profile_id = client.profile.id
    
        ac_groups = client.get_groups(
            prefix=f"{venue_id}/Submission{submission_number}/Area_Chair_",
            signatory=profile_id,
        )
        if not ac_groups:
            return f"Could not find your AC group for Submission #{submission_number}."
    
        ac_anon_id = ac_groups[0].id
        reviewer_group = f"{venue_id}/Submission{submission_number}/{reviewer_id}"
    
        readers = [
            f"{venue_id}/Program_Chairs",
            f"{venue_id}/Submission{submission_number}/Senior_Area_Chairs",
            f"{venue_id}/Submission{submission_number}/Area_Chairs",
            reviewer_group,
        ]
    
        # Resolve the submission to get forum/replyto eagerly
        note = _resolve_submission(client, venue_id, submission_number=submission_number)
        note_forum = note.id if note else None
        note_replyto = note.id if note else None
    
        payload = {
            "invitation": f"{venue_id}/Submission{submission_number}/-/Official_Comment",
            "signatures": [ac_anon_id],
            "note_forum": note_forum,
            "note_replyto": note_replyto,
            "readers": readers,
            "content": {
                "title": {"value": subject},
                "comment": {"value": message_text},
            },
        }
        readers_display = "\n".join(f"  - {r}" for r in readers)
        preview = "\n".join([
            f"## Message to {reviewer_id} (Submission #{submission_number})",
            f"**From:** {ac_anon_id}",
            f"**Subject:** {subject}",
            f"**Visible to:**\n{readers_display}",
            f"\n{message_text}",
        ])
        confirmation_id = pending_store.add(action="message_reviewer", payload=payload, preview=preview)
        return f"{preview}\n\n---\n**Confirmation ID:** `{confirmation_id}`\n\nCall `confirm_submission` with this ID to send the message."
Behavior4/5

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

With no annotations, the description carries the full burden. It successfully discloses visibility scope (who sees the message) and the preview/confirmation pattern. Could mention error handling or idempotency, but covers the essential behavioral traits beyond schema structure.

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?

Well-structured with purpose first, visibility constraints, behavioral workflow, then parameter details. Every sentence provides distinct value. Appropriate length given the need to document 5 undocumented parameters.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Complete for a tool with output schema (acknowledges 'Returns a preview' without redundant detailing). Covers privacy implications, two-step workflow, and all parameters. Sufficient for correct agent invocation despite zero schema descriptions.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% description coverage, but the description fully compensates by documenting all 5 parameters in the Args section. Adds valuable semantic context, particularly the format example for reviewer_id ('e.g., Reviewer_ABCD').

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?

States specific verb ('Send') + resource ('private message') + scope ('to a specific reviewer'). Distinguishes from sibling 'post_comment' by emphasizing privacy and specific audience ('Visible to the reviewer, ACs, SACs, and PCs').

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

Usage Guidelines5/5

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

Explicitly states the critical workflow constraint: 'Returns a preview — call confirm_submission to actually send it.' This clearly indicates the tool requires a follow-up confirmation step and names the specific sibling tool to use.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/michaelqshieh/openreview-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server