Skip to main content
Glama

get_reviews

Retrieve official reviews for conference submissions by providing venue and paper identifiers to support reviewer workflows.

Instructions

Get all official reviews for a submission.

Args: venue_id: The venue identifier (e.g., 'ICLR.cc/2025/Conference'). submission_id: The submission's note ID. Provide this OR submission_number. submission_number: The paper number. Provide this OR submission_id.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
venue_idYes
submission_idNo
submission_numberNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The handler function `get_reviews` fetches official reviews for a specific submission from OpenReview using the provided venue and submission identifiers.
    async def get_reviews(
        venue_id: str,
        submission_id: str | None = None,
        submission_number: int | None = None,
    ) -> str:
        """Get all official reviews for a submission.
    
        Args:
            venue_id: The venue identifier (e.g., 'ICLR.cc/2025/Conference').
            submission_id: The submission's note ID. Provide this OR submission_number.
            submission_number: The paper number. Provide this OR submission_id.
        """
        client = get_client()
        paper_number = submission_number
        if submission_id and not paper_number:
            note = client.get_note(submission_id)
            paper_number = note.number
        if paper_number is None:
            return "Please provide either submission_id or submission_number."
    
        reviews = client.get_all_notes(
            invitation=f"{venue_id}/Submission{paper_number}/-/Official_Review"
        )
        if not reviews:
            return f"No reviews found for Submission #{paper_number}."
    
        lines = [f"## Reviews for Submission #{paper_number} ({len(reviews)} total)\n"]
        for review in reviews:
            sig = review.signatures[0] if review.signatures else "Unknown"
            reviewer_short = sig.split("/")[-1] if "/" in sig else sig
            content = review.content
            rating = content.get("rating", {}).get("value", "N/A")
            confidence = content.get("confidence", {}).get("value", "N/A")
            title = content.get("title", {}).get("value", "")
            text = content.get("review", {}).get("value", "No review text")
            date_str = ""
            if review.cdate:
                dt = datetime.fromtimestamp(review.cdate / 1000, tz=timezone.utc)
                date_str = f" ({dt.strftime('%Y-%m-%d')})"
            lines.append(f"### {reviewer_short}{date_str}")
            lines.append(f"**Rating:** {rating} | **Confidence:** {confidence}")
            if title:
                lines.append(f"**Title:** {title}")
            lines.append(f"\n{text}\n")
            lines.append("---\n")
        return "\n".join(lines)
  • Registration of the `get_reviews` tool using the @mcp.tool decorator.
    @mcp.tool()
Behavior3/5

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

No annotations provided, so description carries full burden. Discloses scope limitation ('official' reviews implies exclusion of comments/drafts), but lacks explicit read-only safety declaration, auth requirements, or error behaviors.

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?

Uses efficient docstring format with 'Args:' section. Purpose statement is front-loaded. Minor redundancy in repeating 'Provide this OR' for both parameters, but necessary for clarity. No wasted sentences.

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?

Given 3 parameters with 0% schema coverage, the description successfully documents all parameters and their relationships. Output schema exists, so return value documentation is unnecessary. Complete for a retrieval tool of this complexity.

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

Parameters4/5

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

Excellent compensation for 0% schema description coverage. Adds semantic meaning ('note ID' vs 'paper number'), provides concrete example for venue_id, and documents the XOR constraint between submission_id and submission_number that schema cannot express.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clear verb-resource combination ('Get all official reviews') with specific scope ('for a submission'). Distinguishes from write-operation siblings like edit_review and submit_review, though it could clarify distinction from get_review_status.

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

Usage Guidelines3/5

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

Provides explicit parameter-level guidance on mutual exclusivity ('Provide this OR submission_number'), which is critical for correct invocation. However, lacks guidance on when to use this versus sibling tools like get_review_status or get_discussion.

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