Skip to main content
Glama

submit_review

Prepare and preview a peer review for academic conference submissions by providing ratings, confidence levels, and detailed feedback before final submission.

Instructions

Prepare a review for submission. Returns a preview — call confirm_submission to actually post it.

Args: venue_id: The venue identifier. submission_number: The paper number. rating: Numerical rating (scale depends on venue). confidence: Your confidence level (scale depends on venue). review_text: The main review text. title: Review title. Default: 'Official Review'. strengths: Paper strengths (if venue uses separate fields). weaknesses: Paper weaknesses (if venue uses separate fields). questions: Questions for the authors. limitations: Limitations discussion. ethics_flag: Whether to flag ethics concerns.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
venue_idYes
submission_numberYes
ratingYes
confidenceYes
review_textYes
titleNoOfficial Review
strengthsNo
weaknessesNo
questionsNo
limitationsNo
ethics_flagNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The handler function 'submit_review' that creates a review entry and adds it to the pending store for confirmation.
    async def submit_review(
        venue_id: str,
        submission_number: int,
        rating: int,
        confidence: int,
        review_text: str,
        title: str = "Official Review",
        strengths: str | None = None,
        weaknesses: str | None = None,
        questions: str | None = None,
        limitations: str | None = None,
        ethics_flag: bool = False,
    ) -> str:
        """Prepare a review for submission. Returns a preview — call confirm_submission to actually post it.
    
        Args:
            venue_id: The venue identifier.
            submission_number: The paper number.
            rating: Numerical rating (scale depends on venue).
            confidence: Your confidence level (scale depends on venue).
            review_text: The main review text.
            title: Review title. Default: 'Official Review'.
            strengths: Paper strengths (if venue uses separate fields).
            weaknesses: Paper weaknesses (if venue uses separate fields).
            questions: Questions for the authors.
            limitations: Limitations discussion.
            ethics_flag: Whether to flag ethics concerns.
        """
        content = {
            "title": {"value": title},
            "review": {"value": review_text},
            "rating": {"value": rating},
            "confidence": {"value": confidence},
        }
        if strengths:
            content["strengths"] = {"value": strengths}
        if weaknesses:
            content["weaknesses"] = {"value": weaknesses}
        if questions:
            content["questions"] = {"value": questions}
        if limitations:
            content["limitations"] = {"value": limitations}
        if ethics_flag:
            content["ethics_flag"] = {"value": "Yes"}
    
        client = get_client()
        profile_id = client.profile.id
        anon_groups = client.get_groups(
            prefix=f"{venue_id}/Submission{submission_number}/Reviewer_",
            signatory=profile_id,
        )
        if not anon_groups:
            return f"Could not find your anonymous reviewer group for Submission #{submission_number}. Are you assigned as a reviewer?"
    
        anon_id = anon_groups[0].id
        payload = {
            "invitation": f"{venue_id}/Submission{submission_number}/-/Official_Review",
            "signatures": [anon_id],
            "content": content,
        }
    
        preview_lines = [
            f"## Review Preview for Submission #{submission_number}",
            f"**Signing as:** {anon_id}",
            f"**Rating:** {rating}",
            f"**Confidence:** {confidence}",
            f"\n### {title}\n",
            review_text,
        ]
        if strengths:
            preview_lines.append(f"\n**Strengths:** {strengths}")
        if weaknesses:
            preview_lines.append(f"\n**Weaknesses:** {weaknesses}")
        if questions:
            preview_lines.append(f"\n**Questions:** {questions}")
    
        preview = "\n".join(preview_lines)
        confirmation_id = pending_store.add(action="submit_review", payload=payload, preview=preview)
        return f"{preview}\n\n---\n**Confirmation ID:** `{confirmation_id}`\n\nCall `confirm_submission` with this ID to post the review to OpenReview."
Behavior4/5

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

With no annotations provided, the description carries the full burden. It successfully discloses the preview behavior, the venue-dependent rating/confidence scales, and conditional field availability. However, it lacks details on auth requirements, idempotency, or whether previews persist between calls.

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

Conciseness4/5

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

The first sentence is efficiently front-loaded with purpose and workflow. While the Args section is lengthy, it is necessary given the zero schema coverage. No redundant or wasted sentences, though the parameter list dominates the description length.

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 an 11-parameter tool with a two-stage submission workflow, no annotations, and zero schema coverage, the description adequately covers the critical path (preview vs. confirm) and all parameter semantics. It appropriately omits return value details since an output schema exists.

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 description coverage is 0%, requiring the description to compensate. The Args section provides clear semantic meaning for all 11 parameters (e.g., 'Numerical rating (scale depends on venue)', 'if venue uses separate fields'), effectively bridging the schema documentation gap.

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 explicitly states the tool 'Prepare[s] a review for submission' and clarifies that it 'Returns a preview,' distinguishing it from the sibling tool confirm_submission. The verb-resource combination is specific and the scope (preview vs. final post) is clearly defined.

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 directs users to 'call confirm_submission to actually post it,' providing a clear alternative and establishing the two-step workflow. This prevents misuse by clarifying that this tool does not finalize the submission.

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