Skip to main content
Glama

arXiv Paper Search Payment Quote

arxiv_search_quote
Read-onlyIdempotent

Returns the payment terms for https://horizonpulse.dev/api/arxiv/search (base $0.003; USDC on Base only); this tool never runs the check or pays. Pay the 402 over HTTP with x402 v2: GET ?q=diffusion transformer (1-8 words; optional category=cs.LG, max=1-20, sort=relevance|submitted|updated). arXiv paper search: up to 20 papers for 1-8 keywords, optional category (cs.AI) and sort (relevance, submitted, updated). Returns title, authors, abstract, categories, dates, DOI and journal ref with abstract-page links; no PDFs. Metadata is CC0 per the arXiv API terms; each response carries the arXiv open access interoperability acknowledgement. Not endorsed by arXiv. No results, bad input or arXiv down: not charged. USDC on Base only.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "arxiv_search_quote"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Annotations only say read-only/idempotent/non-destructive; the description adds substantive behavior: fixed base price of $0.003, USDC on Base only, no charge on failure, metadata licensing (CC0, arXiv acknowledgement), no PDFs, and no arXiv endorsement. That is pricing, settlement, and failure semantics the annotations cannot convey.

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?

Core purpose, price, and the 'never executes' constraint are front-loaded. There is some redundancy: 'USDC on Base only' appears twice and the arXiv search capability is restated in a separate sentence, but nothing is off-topic enough to obscure the point.

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?

With no input or output schema, the description carries the load and mostly does: it explains what the quote covers, how to settle it, what the downstream search returns, and when charges do or do not apply. It never enumerates the fields of the quote response itself, which is the one remaining gap.

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?

The tool takes zero parameters, so the schema baseline is 4. The description goes beyond that by documenting the upstream request shape the agent must construct over HTTP (q as 1-8 words, optional category, max 1-20, sort enum), which is genuinely useful even though it is not this tool's input.

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 first sentence names a specific verb and resource ('Returns the payment terms') plus the exact target endpoint, and immediately scopes it against the obvious confusion: 'this tool never runs the check or pays.' An agent can tell this apart from a live arXiv search sibling 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?

It states the operational path clearly: pay the 402 over HTTP with x402 v2, and this tool is only for the quote. It also tells the agent what is free ('No results, bad input or arXiv down: not charged'). It stops short of naming any sibling quote tools or saying when a quote is required versus optional, which keeps it at 4 rather than 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.