Skip to main content
Glama

Openreview

by io.github.pipeworx-io

List Submissions

list_submissions
Read-onlyIdempotent

Papers submitted to an academic CONFERENCE venue on OpenReview — ICLR, NeurIPS, ICML, COLM and similar. PREFER for "ICLR 2024 papers about diffusion models", "NeurIPS submissions on RLHF", "what did ICML publish on optimizers". Pass the venue group id as venue_id (use list_venues to find it) together with a topic in query.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNocdate (creation date, default desc) | tmdate (modify date) | number
limitNo1-1000 (default 25)
queryNoTopic to search for within the venue, e.g. "diffusion models". Required in practice — OpenReview no longer serves an unfiltered listing to automated clients.
offsetNo0-based offset
venue_idYesVenue group id (e.g. "ICLR.cc/2024/Conference")

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoTotal number of matching submissions
notesNoList of submission notes

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed2 schema fields changed
    • changedInput schema / examples
      Previous value: -[
-  {
-    "venue_id": "ICLR.cc/2024/Conference"
-  },
-  {
-    "limit": 50,
-    "offset": 0,
-    "sort": "cdate",
-    "venue_id": "NeurIPS.cc/2024/Conference"
-  }
-]New value: +[
+  {
+    "query": "transformer",
+    "venue_id": "ICLR.cc/2024/Conference"
+  },
+  {
+    "limit": 50,
+    "offset": 0,
+    "query": "reinforcement learning from human feedback",
+    "venue_id": "NeurIPS.cc/2024/Conference"
+  }
+]
    • addedInput schema / properties / query
      Added value: +{
+  "description": "Topic to search for within the venue, e.g. \"diffusion models\". Required in practice — OpenReview no longer serves an unfiltered listing to automated clients.",
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "venue_id": "ICLR.cc/2024/Conference"
+  },
+  {
+    "limit": 50,
+    "offset": 0,
+    "sort": "cdate",
+    "venue_id": "NeurIPS.cc/2024/Conference"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "description": "Total number of matching submissions",
+      "type": "number"
+    },
+    "notes": {
+      "description": "List of submission notes",
+      "items": {
+        "properties": {
+          "content": {
+            "description": "Note content fields",
+            "type": "object"
+          },
+          "forum": {
+            "description": "Forum (paper) id",
+            "type": "string"
+          },
+          "id": {
+            "description": "Note identifier",
+            "type": "string"
+          },
+          "replies": {
+            "description": "Child notes if requested",
+            "type": "array"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}
  3. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Annotations already declare readOnly, openWorld, idempotent, and non-destructive behavior. The description adds useful behavioral context beyond annotations: it is scoped to OpenReview conference papers, and the venue_id plus a topic query are required in practice. No contradiction with annotations exists.

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?

Two tight sentences, each earning its place: the first defines scope and venue types, the second gives usage examples and invocation guidance. No filler, no repetition of schema content.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only list/search tool with a full input schema, output schema, and safety annotations, the description covers purpose, target domain, preferred use cases, required venue_id resolution, and the practical need for a query. Nothing essential is missing for correct selection and invocation.

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 coverage is 100%, so the baseline is 3. The description adds value by clarifying that venue_id is the OpenReview venue group id and instructing the agent to discover it via list_venues, and by stressing that the tool needs a topic in query, not just an unfiltered venue listing.

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 specifies a concrete verb-resource pair: listing papers submitted to an academic CONFERENCE venue on OpenReview. It names concrete venues (ICLR, NeurIPS, ICML, COLM) and gives example user queries, making the tool's purpose immediately recognizable and distinct from siblings like list_venues or get_paper.

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 gives clear when-to-use guidance via 'PREFER for' and concrete query examples, and explicitly directs the agent to use list_venues to obtain venue_id. It does not explicitly state when NOT to use this tool or name alternative search tools, so it falls just short of full usage coverage.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

All Openreview toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.5/5.0
Disambiguation2/5

The tool set includes both OpenReview-specific tools (e.g., get_paper, list_submissions) and a large number of unrelated tools for Pipeworx, Polymarket, and SEC filings. While individual descriptions are clear, the mix of domains creates confusion about which tools to use for a given task, leading to potential misselection.

Naming Consistency2/5

Tool names follow inconsistent patterns: some use underscore_case (ai_visibility_check, generate_llms_txt), some are verb_noun (get_paper, list_venues), and others use descriptive phrases (ask_pipeworx_grounded, polymarket_arbitrage). The lack of a unified naming scheme makes the tool set feel disjointed.

Tool Count2/5

With 37 tools, the count is too high for a server supposedly focused on OpenReview. Only about 6 tools are directly related to OpenReview; the rest are for unrelated domains like prediction markets, data retrieval, and memory management. The scope is unclear and overloaded.

Completeness2/5

For the OpenReview domain, the tool set covers basic retrieval (get_paper, search_notes, list_submissions) but lacks operations like creating or updating notes, which are common in a review platform. The inclusion of many non-OpenReview tools does not compensate for these gaps, leaving the surface incomplete for its stated purpose.

Resources