Skip to main content
Glama

Openreview

by io.github.pipeworx-io

Search Notes

search_notes
Read-onlyIdempotent

Full-text search across OpenReview notes (papers, reviews, decisions) by query string; optionally restrict to a content field (e.g. title, abstract) or filter by author signature; returns matching note ids, titles, and venues.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNo1-1000 (default 25)
queryYesFree-text query
offsetNo0-based offset
venue_idNoRestrict to one venue group id, e.g. "ICLR.cc/2024/Conference" (use list_venues to find it).
signatureNoFilter by signature group (e.g. author profile id)
content_fieldNoRestrict to a content field (e.g. "title", "abstract")

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
countNoTotal number of matching notes
notesNoSearch results

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: -[
-  {
-    "query": "transformer attention mechanism"
-  },
-  {
-    "content_field": "abstract",
-    "limit": 50,
-    "query": "neural scaling laws"
-  }
-]New value: +[
+  {
+    "query": "transformer attention mechanism"
+  },
+  {
+    "limit": 10,
+    "query": "diffusion",
+    "venue_id": "ICLR.cc/2024/Conference"
+  },
+  {
+    "content_field": "abstract",
+    "limit": 50,
+    "query": "neural scaling laws"
+  }
+]
    • addedInput schema / properties / venue_id
      Added value: +{
+  "description": "Restrict to one venue group id, e.g. \"ICLR.cc/2024/Conference\" (use list_venues to find it).",
+  "type": "string"
+}
  2. Changed2 schema fields changed
    • addedInput schema / examples
      Added value: +[
+  {
+    "query": "transformer attention mechanism"
+  },
+  {
+    "content_field": "abstract",
+    "limit": 50,
+    "query": "neural scaling laws"
+  }
+]
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
+  "properties": {
+    "count": {
+      "description": "Total number of matching notes",
+      "type": "number"
+    },
+    "notes": {
+      "description": "Search results",
+      "items": {
+        "properties": {
+          "content": {
+            "description": "Note content fields",
+            "type": "object"
+          },
+          "forum": {
+            "description": "Forum (paper) id",
+            "type": "string"
+          },
+          "id": {
+            "description": "Note identifier",
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "type": "array"
+    }
+  },
+  "type": "object"
+}
  3. First observed

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already establish readOnlyHint, idempotentHint, and non-destructive behavior, so the description doesn't need to restate those. It adds useful behavioral context by naming the searched content (papers, reviews, decisions) and the return shape (ids, titles, venues). It stops short of describing result ordering or pagination details, but the schema covers limit/offset.

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?

A single sentence front-loads the core purpose, then efficiently adds optional filters and return contents. There is no wasted wording and every clause earns its place.

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 output schema and full parameter documentation, the description covers the essential facts an agent needs: what is searched, what can be filtered, and what is returned. It is slightly incomplete only in not routing the agent away from sibling search tools and not mentioning any ordering semantics.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the input schema already documents all six parameters with meaningful descriptions. The description reinforces optional filters like content_field and signature, but adds no significant parameter meaning beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description states a specific verb and resource ('full-text search across OpenReview notes'), plus optional filters and return fields. It is clear but does not explicitly name or differentiate itself from sibling tools like search_within, so it doesn't reach the top score.

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

Usage Guidelines3/5

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

The description implies when to use the tool—searching OpenReview notes by query string—and lists optional filters. However, it provides no explicit guidance about when not to use it or which sibling tool would be a better alternative.

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