Skip to main content
Glama
Sign In
Crawlora-org

Crawlora MCP

Official
by Crawlora-org
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Remote

research_search_papers

Search arXiv research papers by query, authors, and publication dates, continuing via cursor; fallback uses OpenAlex index when arXiv is rate limited or unavailable.

Instructions

Search research papers. Search arXiv papers with an owner-bound frozen result window and cursor-only continuation. When arXiv is rate limited or unavailable, an undated search is answered from OpenAlex's index of arXiv papers and the response says so in coverage and warnings.

Input Schema

NameRequiredDescriptionDefault
qNoRequired for initial search; omit on cursor continuation
limitNoPage size (1–50; default 10)
cursorNoOwner-bound continuation cursor (cursor-only with optional limit)
authorsNoAuthor names (up to five; 256 characters each)
sourcesNoEnabled paper sources
published_toNoInclusive publication date (YYYY-MM-DD)
published_fromNoInclusive publication date (YYYY-MM-DD)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv1.17.12

TDQS

A3.7/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the frozen result-window semantics, the owner-bound cursor continuation, and a documented degradation path (OpenAlex index fallback with coverage and warnings signaled in the response). It omits auth/permission requirements and the rate-limit thresholds that trigger the fallback.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three tight sentences with the purpose front-loaded, followed by mechanism and fallback. No repetition or filler, though the final sentence is somewhat dense and could be split for scanability.

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?

No annotations and no output schema, so the description must carry the load, and it covers the two behaviors an agent most needs: how continuation works and what happens on source failure. It stops short of describing result contents or what 'coverage and warnings' actually look like in the response.

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 schema already documents all seven parameters and baseline 3 applies. The description clarifies the cursor contract (cursor-only continuation, owner-bound) and implies an undated-versus-dated search mode, but adds little about q, limit, authors, or the source enum.

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?

States a specific verb and resource ('Search research papers') and then pins down the mechanism: arXiv, an owner-bound frozen result window, and cursor-only continuation. That mechanism detail distinguishes it from generic research siblings, though it never names the sibling it is not (research_related_papers, research_read_paper).

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?

It supplies one concrete usage condition - undated searches fall back to OpenAlex when arXiv is rate limited or unavailable - and implies cursor-only continuation. It never says when to prefer this tool over research_related_papers or research_read_paper, nor when a query must be dated versus undated, so routing guidance stays implied.

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

Deploy Server

Other Tools