Skip to main content
Glama

get_discussion

Retrieve all discussion comments for a submission, including rebuttals, reviewer responses, and area chair comments, to facilitate conference review workflows.

Instructions

Get all discussion comments on a submission (rebuttals, reviewer responses, AC comments).

Args: venue_id: The venue identifier. 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

  • Implementation of the get_discussion tool which retrieves and formats discussion comments for a submission.
    async def get_discussion(
        venue_id: str,
        submission_id: str | None = None,
        submission_number: int | None = None,
    ) -> str:
        """Get all discussion comments on a submission (rebuttals, reviewer responses, AC comments).
    
        Args:
            venue_id: The venue identifier.
            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()
        note = _resolve_submission(client, venue_id, submission_id, submission_number)
        if not note:
            return "Submission not found."
    
        all_notes = client.get_all_notes(forum=note.id)
        comments = []
        for n in all_notes:
            if n.id == note.id:
                continue
            invitations = n.invitations or []
            is_review = any(
                inv.endswith("Official_Review") or inv.endswith("Meta_Review") or inv.endswith("Decision")
                for inv in invitations
            )
            if not is_review:
                comments.append(n)
    
        if not comments:
            return f"No discussion comments found for Submission #{note.number}."
    
        comments.sort(key=lambda c: c.cdate or 0)
        lines = [f"## Discussion for Submission #{note.number} ({len(comments)} comment(s))\n"]
    
        for comment in comments:
            sig = comment.signatures[0] if comment.signatures else "Unknown"
            author_short = sig.split("/")[-1] if "/" in sig else sig
            text = comment.content.get("comment", {}).get("value", "")
            if not text:
                text = comment.content.get("rebuttal", {}).get("value", "")
            if not text:
                for key, val in comment.content.items():
                    if isinstance(val, dict) and "value" in val and isinstance(val["value"], str):
                        text = val["value"]
                        break
            title = comment.content.get("title", {}).get("value", "")
            date_str = ""
            if comment.cdate:
                dt = datetime.fromtimestamp(comment.cdate / 1000, tz=timezone.utc)
                date_str = f" ({dt.strftime('%Y-%m-%d %H:%M UTC')})"
            readers_str = ", ".join(comment.readers) if comment.readers else "N/A"
            inv_names = [inv.split("/")[-1] for inv in (comment.invitations or [])]
            lines.append(f"### {author_short}{date_str}")
            if title:
                lines.append(f"**{title}**")
            lines.append(f"*Type: {', '.join(inv_names)}* | *Visible to: {readers_str}*")
            lines.append(f"\n{text}\n")
            lines.append("---\n")
        return "\n".join(lines)
Behavior2/5

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

No annotations provided, so description carries full disclosure burden. 'Get all' implies a read-only operation, but the description lacks critical behavioral details: authentication requirements, authorization scope (who can view these discussions?), rate limiting, or whether 'all' includes private vs public comments. No contradiction with annotations.

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?

Front-loaded purpose statement followed by structured Args documentation. Efficient with no redundant prose. Slightly informal docstring format ('Args:') differs from typical MCP description style but remains highly readable and functional.

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 the presence of an output schema (removing need to describe return values) and relatively simple 3-parameter structure, the description adequately covers the tool's operation. Could improve by mentioning validation behavior when both submission identifiers are provided or authorization prerequisites.

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. The Args section documents all 3 parameters (venue_id, submission_id, submission_number) and crucially explains the relationship logic (mutual exclusivity) between the two submission identifiers. Deducted one point for lacking format specifications (e.g., venue_id string format, integer ranges).

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?

Clear verb 'Get' with specific resource 'discussion comments' and scope 'on a submission'. The parenthetical examples (rebuttals, reviewer responses, AC comments) effectively distinguish this from sibling tools like get_reviews (formal evaluations) and get_submission (paper metadata).

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

Usage Guidelines4/5

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

Provides explicit parameter-level guidance clarifying the XOR relationship between submission_id and submission_number ('Provide this OR...'). While it doesn't explicitly name sibling alternatives for tool selection, the content examples (rebuttals vs reviews) provide clear contextual boundaries for appropriate 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