Skip to main content
Glama

OpenArx

by ai.openarx
OverviewDiscussionsAdmin

search

Hybrid semantic + keyword search across scientific papers. Combines vector similarity with BM25 full-text matching for both conceptual queries and exact terms (paper IDs, author names). Supports filtering by content type (methodology / results / theoretical / etc.), entities, categories, and date range. Default mode for general queries — use 'search_keyword' for exact-term lookups or 'search_semantic' for pure paraphrase queries.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
limitNoMax results to return
queryYesSearch query text
dateToNoFilter: published on or before (ISO date)
detailNo'minimal' = id+title+snippet+score. 'standard' = adds metadata + chunkContext. 'full' = adds entities/selfContained/scores/licenses map
facetsNoIf true, return facets block: count breakdown by contentType + top entities mentioned
run_idNoOptional. The active methodist run_id (as returned by the methodist diagnose / get_current_dose door). Pass it whenever you call this tool while working inside a run, so the call is attributed to that run for the §8 usage crosscheck — attribution is run-anchored, so it stays correct even if your access token refreshes mid-run. Must be YOUR run: a run_id owned by a different principal, or a non-existent run_id, is rejected.
dateFromNoFilter: published on or after (ISO date)
entitiesNoSoft filter by entity (method names like "BERT", datasets like "SQuAD", metrics like "BLEU"), case-insensitive. Matching chunks rank first; chunks with no entities recorded (legacy gap) fall to the bottom rather than being dropped; chunks with non-matching entities are excluded.
strategyNo'fast' (~1s) for quick lookups; 'rerank' (~10s) applies cross-encoder for higher relevance on complex queriesfast
categoriesNoFilter by arXiv categories (e.g. cs.AI, cs.LG)
contentTypeNoFilter chunks by type. Use [methodology] to find HOW researchers approach a problem; [results] for OUTCOMES; [survey, background] for context
diversifyByNo'document' (default): max N chunks per paper. 'keyConcept': diversify by main idea (good for landscape view). 'contentType': mix methodology/results/etc.document
vectorModelNo'gemini' for general semantic queries (default); 'specter2' for scientific paper similarity. ★ COVERAGE DIFFERS: the specter2 space does not cover the whole corpus — 77,782 chunks carry no vector in it and are therefore INVISIBLE to a specter2 search, not merely ranked lower. An empty result there means 'not indexed in this space', which is indistinguishable from 'nothing similar exists'. Use gemini when completeness matters; use specter2 to re-rank or corroborate.gemini
maxPerDocumentNoMax chunks per single key (only when diversifyBy=document)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • removedInput schema / properties / detail / default
      Removed value: -"full"
  2. Changed1 schema field changed
    • changedInput schema / properties / detail / default
      Previous value: -"standard"New value: +"full"
  3. Changed1 schema field changed
    • changedInput schema / properties / vectorModel / description
      Previous value: -"'gemini' for general semantic queries (default); 'specter2' for scientific paper similarity"New value: +"'gemini' for general semantic queries (default); 'specter2' for scientific paper similarity. ★ COVERAGE DIFFERS: the specter2 space does not cover the whole corpus — 77,782 chunks carry no vector in it and are therefore INVISIBLE to a specter2 search, not merely ranked lower. An empty result there means 'not indexed in this space', which is indistinguishable from 'nothing similar exists'. Use gemini when completeness matters; use specter2 to re-rank or corroborate."
  4. First observed

TDQS

A4.4/5.0
Behavior4/5

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

No annotations are provided, so the description carries the burden. It discloses that the tool combines vector similarity with BM25 full-text matching, which is a meaningful behavioral trait beyond a simple search label. It does not explicitly state read-only guarantees or result ordering, but the search nature and schema descriptions cover most of the remaining context.

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?

Three sentences deliver purpose, capability, and routing with no redundancy. Each sentence earns its place and the key differentiator is front-loaded.

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 tool with 14 parameters and no output schema, the description provides the essential high-level orientation, while the schema fully documents the parameters. Return-payload details are covered by the detail parameter's enum rather than the description, which is acceptable given the schema's richness.

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 description coverage is 100%, so the baseline is 3. The description lists filters (content type, entities, categories, date range) already present in the schema and adds no parameter-level details beyond noting exact terms like paper IDs and author names.

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 states a specific verb and resource: 'search across scientific papers', and explains the hybrid semantic + keyword approach. It differentiates from siblings by naming search_keyword and search_semantic and positioning itself as the default for general queries.

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 gives routing guidance: 'Default mode for general queries — use search_keyword for exact-term lookups or search_semantic for pure paraphrase queries.' This tells the agent when to use this tool and when to choose an alternative.

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

All OpenArx toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources