doc.page PDF Extraction

extract_pdf

Extract a PDF into clean Markdown and structured elements (headings, paragraphs). Returns the canonical ExtractedDocument object. mode "hybrid" runs a heavier semantic engine that also reconstructs tables and bounding boxes; the default "fast" engine is prose-only (low confidence.tables).

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": {
      "url": "<url>"
    },
    "name": "extract_pdf"
  }
}

Input Schema

Name	Required	Description
`url`	Yes	http(s) URL of the PDF to extract.
`mode`	No	fast = prose engine. hybrid = semantic engine with tables + bounding boxes when deployed; falls back to fast with a warning otherwise.
`outputs`	No	Subset of outputs to include. Default: markdown and elements.
`chunkTokens`	No	Target chunk size in tokens (when chunks are requested). Default 512.

Schema Changelog

Changes observed during successful MCP inspections.

Changed4 schema fields changedJul 13, 2026

changedInput schema / properties / chunkTokens / description

Previous value: -"Tamaño objetivo de chunk en tokens (si se piden chunks). Por defecto 512."New value: +"Target chunk size in tokens (when chunks are requested). Default 512."

changedInput schema / properties / mode / description

Previous value: -"fast = server-pdfjs (prosa). hybrid = server-opendataloader (tablas + bounding boxes) si está desplegado; si no, cae a fast con un warning."New value: +"fast = prose engine. hybrid = semantic engine with tables + bounding boxes when deployed; falls back to fast with a warning otherwise."

changedInput schema / properties / outputs / description

Previous value: -"Subconjunto de salidas a incluir. Por defecto: markdown y elements."New value: +"Subset of outputs to include. Default: markdown and elements."

changedInput schema / properties / url / description

Previous value: -"URL http(s) del PDF a extraer."New value: +"http(s) URL of the PDF to extract."

First observedJul 12, 2026

TDQS

A4.2/5.0

Behavior4/5

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

With no annotations, the description must carry the transparency burden. It discloses the return type (ExtractedDocument), mode differences, and fallback behavior for hybrid. However, it does not mention error handling or side effects, which is a minor gap.

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?

The description is three sentences, front-loading the core purpose and return type, then details on modes. Every sentence adds critical information with zero redundancy or fluff.

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?

Despite no output schema, the description clarifies the return value is the canonical ExtractedDocument object and lists structural elements. It lacks explanation of error conditions or input constraints like file size, but covers the main use case well.

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?

All parameters have schema descriptions (100% coverage), so the baseline is 3. The description adds significant value for the 'mode' parameter by explaining engine differences and fallback behavior, slightly elevating it above baseline.

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 description clearly states the tool extracts a PDF to clean Markdown and structured elements, with a specific verb ('Extract') and resource ('PDF'). It distinguishes from siblings like list_tables and get_chunks by focusing on full document extraction.

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?

The description explains when to use fast vs hybrid mode, but it does not provide explicit guidance on when to use this tool versus alternatives like list_tables for table extraction. This lack of cross-tool comparisons leaves usage partially ambiguous.

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

All doc.page PDF Extraction 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?