A.U.G.U.R Synapse · Web & Research

arXiv paper search

arxiv_search

Read-onlyIdempotent

Search arXiv research papers by keywords, author or category — newest or most relevant — with abstracts, authors, dates and PDF links. arXiv's official API. query supports arXiv syntax (ti:, au:, abs:, cat:cs.AI, AND/OR). Paced to arXiv's one-request-per-3-seconds policy and cached, so repeated queries are instant. Price: $0.001 per call (10 free/day; after that a payment-required result lists x402 options). Errors: returns isError with a message for invalid input or an upstream failure (not charged).

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "query": "<query>"
    },
    "name": "arxiv_search"
  }
}

Input Schema

Name	Required	Description	Default
`sort`	No	Order by relevance to the query or by submission date. One of "relevance", "newest". Default "relevance".	relevance
`limit`	No	How many papers to return. Range 1-30. Default 10.
`query`	Yes	e.g. "tool use agents" or au:hinton or cat:cs.CL AND ti:reasoning

Output Schema

Name	Required	Description	Default
`query`	No
`papers`	No
`total_results`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedSep 28, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/openWorld, and the description adds substantive traits beyond them: 1-request-per-3-second pacing, caching behavior, the $0.001/call price with 10 free/day and x402 payment fallback, and error semantics (isError on invalid input/upstream failure, not charged). This is exactly the extra context an agent needs before calling.

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?

Purpose is front-loaded in the first clause, and each subsequent sentence covers a distinct concern (query syntax, pacing/caching, pricing, errors) with no filler. Dense but every sentence earns its place.

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?

An output schema exists so return values need not be re-explained, and the description still sketches the payload (abstracts, authors, dates, PDF links). Pricing, rate limits, caching, and error behavior are all covered, leaving no material gap for correct 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 arXiv query-syntax semantics beyond the schema's examples (ti:, au:, abs:, cat:cs.AI, AND/OR), clarifying what the required 'query' string actually accepts. Sort and limit are already fully documented in the schema.

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?

States a specific verb and resource ('Search arXiv research papers') plus scope (keywords, author, category) and sort modes. It is clearly distinguishable from siblings like book_search, hn_search, wiki, and doi_lookup without opening any schema.

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?

Gives clear context for when this tool applies (arXiv academic literature) and notes the two sort intents, but never names an alternative or a when-not condition (e.g. vs. doi_lookup for DOI resolution or web_read for arbitrary pages). Clear context, no explicit exclusions.

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

All A.U.G.U.R Synapse · Web & Research tools Inspect

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

Need Help?