Cortexa research tool·literature·arxiv

ArXiv Get Pdf Snippets

Fetch an arXiv paper's PDF and return bounded text snippets around provided terms. Uses markitdown to convert PDF to markdown. All arXiv papers are freely available (no paywall). Useful when key details are in the full text rather than abstract.

Livelast probed 2026-04-30 23:07Z· 6212msCortexa

Status

The most recent probe succeeded. Safe to call from the agent today.

Last probed: 1d ago
Last success: 1d ago
Last latency: 6212ms

Schema

JSON Schema the agent (or your API call) must match.

{
  "properties": {
    "arxiv_id": {
      "description": "arXiv paper ID (e.g., '2301.12345' or 'arXiv:2301.12345'). The tool will build the PDF URL automatically.",
      "type": "string"
    },
    "max_snippets_per_term": {
      "default": 3,
      "description": "Maximum number of snippets returned per term.",
      "maximum": 10,
      "minimum": 1,
      "type": "integer"
    },
    "max_total_chars": {
      "default": 8000,
      "description": "Hard cap on total characters returned across all snippets.",
      "maximum": 50000,
      "minimum": 1000,
      "type": "integer"
    },
    "pdf_url": {
      "description": "Direct PDF URL (e.g., 'https://arxiv.org/pdf/2301.12345.pdf').",
      "type": "string"
    },
    "terms": {
      "description": "Terms to search for in the extracted full text (case-insensitive).",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "window_chars": {
      "default": 220,
      "description": "Context window size (characters) before and after each match.",
      "maximum": 2000,
      "minimum": 20,
      "type": "integer"
    }
  },
  "required": [
    "terms"
  ],
  "type": "object"
}

Examples (1)

Default ArXiv Get Pdf Snippets call

public-safeinput

{
  "max_snippets_per_term": 1,
  "max_total_chars": 1,
  "terms": [],
  "window_chars": 1
}

Expected response keys: success

Anonymous-safe example. Rate-limited; no sign-in required.

Identifiers

Catalog ID: tu_ArXiv_get_pdf_snippets
Tool name: ArXiv_get_pdf_snippets
Added: 2026-04-30 22:47Z
Tags: tooluniverse

Schema

JSON Schema the agent (or your API call) must match.

{ "properties": { "arxiv_id": { "description": "arXiv paper ID (e.g., '2301.12345' or 'arXiv:2301.12345'). The tool will build the PDF URL automatically.", "type": "string" }, "max_snippets_per_term": { "default": 3, "description": "Maximum number of snippets returned per term.", "maximum": 10, "minimum": 1, "type": "integer" }, "max_total_chars": { "default": 8000, "description": "Hard cap on total characters returned across all snippets.", "maximum": 50000, "minimum": 1000, "type": "integer" }, "pdf_url": { "description": "Direct PDF URL (e.g., 'https://arxiv.org/pdf/2301.12345.pdf').", "type": "string" }, "terms": { "description": "Terms to search for in the extracted full text (case-insensitive).", "items": { "type": "string" }, "type": "array" }, "window_chars": { "default": 220, "description": "Context window size (characters) before and after each match.", "maximum": 2000, "minimum": 20, "type": "integer" } }, "required": [ "terms" ], "type": "object" }