Cortexa research tool·literature·semantic_scholar

SemanticScholar Get Pdf Snippets

Fetch a paper's open-access PDF from Semantic Scholar and return bounded text snippets around provided terms. Uses markitdown to convert PDF to markdown. Useful when key details (methods, experimental parameters) are in the full text rather than abstract.

Livelast probed 2026-04-30 23:07Z· 5102msCortexa

Status

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

Last probed: 1d ago
Last success: 1d ago
Last latency: 5102ms

Schema

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

{
  "properties": {
    "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"
    },
    "open_access_pdf_url": {
      "description": "Direct open access PDF URL (recommended when you already have it from SemanticScholar_search_papers).",
      "type": "string"
    },
    "paper_id": {
      "description": "Semantic Scholar paper ID (e.g., from SemanticScholar_search_papers). The tool will fetch the PDF URL if available.",
      "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 SemanticScholar 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_SemanticScholar_get_pdf_snippets
Tool name: SemanticScholar_get_pdf_snippets
Added: 2026-04-30 22:47Z
Tags: tooluniverse

SemanticScholar Get Pdf Snippets

Livelast probed 2026-04-30 23:07Z· 5102msCortexa

Schema

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

{ "properties": { "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" }, "open_access_pdf_url": { "description": "Direct open access PDF URL (recommended when you already have it from SemanticScholar_search_papers).", "type": "string" }, "paper_id": { "description": "Semantic Scholar paper ID (e.g., from SemanticScholar_search_papers). The tool will fetch the PDF URL if available.", "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" }