Skip to main content
Glama

get_pdf

Download submission PDFs from OpenReview conferences using venue ID and submission identifier to access paper content for review workflows.

Instructions

Download a submission's PDF and return the file path so you can read it.

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 submission's 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 `get_pdf` function is a tool that downloads a submission's PDF file from OpenReview and saves it to a local temporary directory, returning the file path.
    async def get_pdf(
        venue_id: str,
        submission_id: str | None = None,
        submission_number: int | None = None,
    ) -> str:
        """Download a submission's PDF and return the file path so you can read it.
    
        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 submission's paper number. Provide this OR submission_id.
        """
        client = get_client()
    
        note_id = submission_id
        if not note_id:
            if submission_number is not None:
                notes = client.get_all_notes(
                    invitation=f"{venue_id}/-/Submission",
                    number=submission_number,
                )
                if not notes:
                    return f"No submission found with number {submission_number} in {venue_id}."
                note_id = notes[0].id
            else:
                return "Please provide either submission_id or submission_number."
    
        pdf_bytes = client.get_pdf(id=note_id)
    
        os.makedirs(PDF_DIR, exist_ok=True)
        safe_id = note_id.replace("/", "_").replace("..", "_")
        filename = f"{safe_id}.pdf"
        filepath = os.path.join(PDF_DIR, filename)
    
        with open(filepath, "wb") as f:
            f.write(pdf_bytes)
    
        return f"PDF downloaded to: {filepath}\n\nYou can now read this file to analyze the paper."
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 adequately describes the core operation (downloading PDF) and return value (file path), but omits safety-critical details such as required permissions, error handling when PDFs are missing, or file system side effects.

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 efficiently structured with the purpose statement front-loaded in the first sentence, followed by a clear Args block. Every sentence serves a distinct purpose—defining the operation, return value, and parameter semantics—with no redundant or wasted content.

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 three-parameter tool with zero schema coverage, the description successfully documents all inputs and their constraints. Since an output schema exists (per context signals), the brief mention of returning a 'file path' is sufficient without detailing the return structure. Minor gaps remain regarding error conditions and authorization requirements.

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?

Given 0% schema description coverage, the description fully compensates by documenting all three parameters in the Args block. It adds crucial semantic meaning including the venue_id format example ('ICLR.cc/2025/Conference'), clarifies submission_id is a 'note ID', and explicitly defines the mutual exclusivity constraint between the two submission identifiers.

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 ('Download') and resources ('submission's PDF') to clearly define the tool's function. It implicitly distinguishes from siblings like get_submission by emphasizing the PDF file path return, indicating this retrieves binary content rather than 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?

The description provides clear context for parameter usage by specifying the mutual exclusivity constraint ('Provide this OR submission_number') for the two submission identifiers. However, it lacks explicit guidance on when to use this tool versus alternatives like get_submission for retrieving submission metadata.

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