Skip to main content
Glama

confirm_submission

Finalize and submit pending reviews, meta-reviews, or comments to OpenReview using a confirmation ID from preview actions.

Instructions

Confirm and submit a pending review, meta-review, or comment to OpenReview.

Args: confirmation_id: The confirmation ID returned by submit_review, submit_meta_review, post_comment, or message_reviewer.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
confirmation_idYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The confirm_submission function handles the submission of pending items to OpenReview by retrieving them from the pending_store and executing the note edit.
    @mcp.tool()
    async def confirm_submission(confirmation_id: str) -> str:
        """Confirm and submit a pending review, meta-review, or comment to OpenReview.
    
        Args:
            confirmation_id: The confirmation ID returned by submit_review, submit_meta_review, post_comment, or message_reviewer.
        """
        item = pending_store.pop(confirmation_id)
        if not item:
            return f"Confirmation ID `{confirmation_id}` not found or already used. Please prepare the submission again."
    
        client = get_client()
        action = item["action"]
        payload = item["payload"]
    
        try:
            edit = _execute_note_edit(client, payload)
            # post_note_edit may return a dict or an Edit object
            if isinstance(edit, dict):
                note_id = edit.get("note", {}).get("id", "unknown")
            else:
                note_obj = getattr(edit, "note", None)
                note_id = getattr(note_obj, "id", "unknown") if note_obj else "unknown"
            action_labels = {
                "submit_review": "Review",
                "edit_review": "Review edit",
                "submit_meta_review": "Meta-review",
                "post_comment": "Comment",
                "message_reviewer": "Message",
            }
            label = action_labels.get(action, "Submission")
            return f"{label} posted successfully to OpenReview.\n\n**Note ID:** {note_id}\n**Action:** {action}"
        except Exception as e:
            pending_store.add(action=item["action"], payload=item["payload"], preview=item["preview"])
            return f"Failed to submit: {e}\n\nThe submission has been preserved — you can try again."
Behavior3/5

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It successfully conveys the two-phase commit pattern (pending → confirmed/submitted) but omits important mutation details like whether confirmation is idempotent, what happens if confirmation fails, or whether pending submissions expire automatically.

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?

The description is front-loaded with the core action in the first sentence, followed by a structured Args section documenting the single parameter. Every sentence serves a purpose; there is no redundant or boilerplate text. The length is appropriate for a single-parameter tool.

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 a low-complexity tool with one parameter and an existing output schema, the description adequately covers the workflow context and parameter semantics. It appropriately references the sibling ecosystem to establish usage patterns, though it could briefly mention what 'pending' status means or confirmation deadlines.

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?

Given 0% schema description coverage (the confirmation_id property has no description in the schema), the Args section effectively compensates by explaining that the parameter is a 'confirmation ID returned by' specific sibling tools, providing crucial provenance context that the schema lacks.

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 uses specific verbs ('Confirm and submit') with clear resources ('pending review, meta-review, or comment') and destination ('OpenReview'). It explicitly distinguishes itself from sibling tools by referencing submit_review, submit_meta_review, post_comment, and message_reviewer as the sources of the required confirmation_id, establishing its role in a two-phase workflow.

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?

The description establishes clear workflow context by stating the confirmation_id is 'returned by' the sibling submission tools, implying this tool must be used after those operations. However, it lacks explicit negative guidance (e.g., when NOT to use this vs. edit_review) or prerequisites like timeout windows for pending submissions.

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