Skip to main content
Glama

PDF в Markdown

pdf_to_markdown

Конвертирует PDF в Markdown (.md) для нейросетей, баз знаний и документации: заголовки, списки, таблицы, ссылки, жирный и курсив. file_url: публичный URL PDF-файла. ocr: скан без текста — сначала распознать (русский и английский); до 100 страниц, цена — как у ocr_pdf.

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": {
      "file_url": "<file_url>"
    },
    "name": "pdf_to_markdown"
  }
}

Input Schema

NameRequiredDescriptionDefault
ocrNo
file_urlYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior4/5

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

Beyond the annotations, it discloses real operational facts: the OCR path supports Russian and English, is capped at 100 pages, and is priced like ocr_pdf. That pricing/limit context is exactly the kind of thing annotations cannot express. It leaves unstated what happens on non-public or inaccessible URLs and whether the result is a file or inline text.

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?

Front-loaded with the conversion outcome, then per-flag notes in a compact telegraphic style; every clause carries information. The compressed, comma-spliced formatting is slightly dense but not wasteful.

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 only two parameters and an output schema already defined, the description covers what an agent needs: the input format, the OCR branch, its limits, and its cost model. Remaining gaps (URL accessibility requirements, failure behavior) are minor for a conversion tool.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description carries the full burden, and it defines both parameters: file_url as a public URL to the PDF and ocr as the opt-in flag for text-free scans, including the language support and 100-page ceiling that constrain its use. This adds meaning well beyond the bare boolean/string types in the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

Names a specific verb and resource (converts PDF to Markdown/.md) and enumerates the preserved structures (headings, lists, tables, links, bold, italics), which implicitly separates it from pdf_to_txt and pdf_to_word. It does not explicitly name those siblings, so the differentiation is inferable rather than stated.

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 concrete use contexts (neural networks, knowledge bases, documentation) and a clear conditional rule for the ocr flag: use it when the PDF is a scan without a text layer. It stops short of explicit exclusions or a direct comparison to pdf_to_txt/ocr_pdf when the input is already plain text or when OCR is the only need.

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.