Skip to main content
Glama

post_comment

Post comments on conference paper submissions with configurable visibility for reviewers and chairs, using a preview-and-confirm system.

Instructions

Post a comment on a submission. Returns a preview — call confirm_submission to post it.

Default readers include ACs, SACs, and PCs. Override with the readers parameter.

Args: venue_id: The venue identifier. submission_number: The paper number. comment_text: The comment text. readers: Who can see this comment. Defaults to ACs + SACs + PCs + Reviewers for the paper.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
venue_idYes
submission_numberYes
comment_textYes
readersNo

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The post_comment function handler, registered as an MCP tool, which posts a comment on a submission and returns a preview for confirmation.
    @mcp.tool()
    async def post_comment(
        venue_id: str,
        submission_number: int,
        comment_text: str,
        readers: list[str] | None = None,
    ) -> str:
        """Post a comment on a submission. Returns a preview — call confirm_submission to post it.
    
        Default readers include ACs, SACs, and PCs. Override with the readers parameter.
    
        Args:
            venue_id: The venue identifier.
            submission_number: The paper number.
            comment_text: The comment text.
            readers: Who can see this comment. Defaults to ACs + SACs + PCs + Reviewers for the paper.
        """
        client = get_client()
        profile_id = client.profile.id
    
        note = _resolve_submission(client, venue_id, submission_number=submission_number)
        if not note:
            return f"Submission #{submission_number} not found."
    
        signer_id = None
        for role_prefix in ["Area_Chair_", "Reviewer_", "Senior_Area_Chair_"]:
            groups = client.get_groups(
                prefix=f"{venue_id}/Submission{submission_number}/{role_prefix}",
                signatory=profile_id,
            )
            if groups:
                signer_id = groups[0].id
                break
        if not signer_id:
            return f"Could not find your anonymous group for Submission #{submission_number}."
    
        if readers is None:
            readers = [
                f"{venue_id}/Program_Chairs",
                f"{venue_id}/Submission{submission_number}/Senior_Area_Chairs",
                f"{venue_id}/Submission{submission_number}/Area_Chairs",
                f"{venue_id}/Submission{submission_number}/Reviewers",
            ]
    
        payload = {
            "invitation": f"{venue_id}/Submission{submission_number}/-/Official_Comment",
            "signatures": [signer_id],
            "note_forum": note.id,
            "note_replyto": note.id,
            "readers": readers,
            "content": {"comment": {"value": comment_text}},
        }
        readers_display = "\n".join(f"  - {r}" for r in readers)
        preview = "\n".join([
            f"## Comment Preview for Submission #{submission_number}",
            f"**Signing as:** {signer_id}",
            f"**Visible to:**\n{readers_display}",
            f"\n{comment_text}",
        ])
        confirmation_id = pending_store.add(action="post_comment", payload=payload, preview=preview)
        return f"{preview}\n\n---\n**Confirmation ID:** `{confirmation_id}`\n\nCall `confirm_submission` with this ID to post the comment."
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/confirmation behavioral pattern and the default visibility model (ACs/SACs/PCs). It does not mention rate limits, authentication requirements, or preview expiration, but covers the critical behavioral traits unique to this tool.

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 description is front-loaded with the core action and workflow constraint in the first two sentences, followed by default behavior, then structured Args documentation. No sentences are wasted; the structure efficiently organizes information for quick parsing by an agent.

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 tool has an output schema (per context signals), the description appropriately focuses on the fact it returns a preview rather than detailing return fields. It covers all 4 parameters (compensating for zero schema coverage), explains the two-step workflow, and clarifies the visibility model, providing sufficient context for an academic conference domain tool.

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?

Schema description coverage is 0%, requiring the description to compensate. The Args section documents all 4 parameters, adding crucial semantic detail for 'readers' (explaining the default visibility and override mechanism) and mapping 'submission_number' to 'paper number.' While venue_id and comment_text are minimally described, the readers explanation provides significant value missing from the schema.

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 clearly states the tool 'Post[s] a comment on a submission' with a specific verb and resource. It distinguishes itself from siblings by clarifying that it only returns a preview and requires calling confirm_submission to finalize, clearly differentiating it from direct-post or read-only tools like get_discussion.

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 defines the workflow: 'Returns a preview — call confirm_submission to post it.' This provides clear guidance on when to use this tool (first step) versus its sibling confirm_submission (second step), preventing the agent from incorrectly assuming the comment is immediately published.

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