Skip to main content
Glama

Распознать текст в PDF

ocr_pdf

Распознаёт текст в сканированном PDF (OCR). Добавляет невидимый текстовый слой. До 100 страниц за раз (больший файл сначала разделите split_pdf); цена — одна единица (как обычный запрос до 10 МБ) за каждые 10 страниц; цена единицы — get_balance (request_price). file_url: публичный URL PDF-файла. languages: список языков (например ["rus","eng"]). По умолчанию: русский + английский.

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": "ocr_pdf"
  }
}

Input Schema

NameRequiredDescriptionDefault
file_urlYes
languagesNo

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare non-read-only, open-world, non-idempotent, non-destructive behavior, so the description's added value is the operational detail: the 100-page cap, the invisible text layer being added to the output, and per-10-page pricing. It does not mention auth or what happens on unsupported/scanned-OCR-failed files, but the cost and limit disclosure is meaningful context beyond the annotations.

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 core purpose, then limits, pricing, and parameter notes in a compact multi-line form with no filler. The pricing sentence is slightly dense (unit cost vs. request_price pointer to get_balance) but every clause carries information.

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?

An output schema exists, so return values need not be explained; the description instead covers the constraints an agent needs — page limit, fallback to split_pdf, cost model, and parameter meaning. Only edge-case behavior (e.g., language code format, failure on non-scanned PDFs) is left unaddressed.

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?

Schema description coverage is 0%, so the description must compensate: it explains that file_url is a public URL to a PDF and that languages is a list such as ["rus","eng"] with a default of Russian + English. Both parameters get semantic meaning absent from the schema, though the expected language code format (ISO 639-2 vs other) is only implied by example.

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?

States a specific verb and resource ('Распознаёт текст в сканированном PDF (OCR)') and specifies the output effect: adds an invisible text layer. This distinguishes it clearly from image-based siblings such as image_to_text and extractors like pdf_to_txt, since the object type and result are stated explicitly.

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 an explicit operational rule — up to 100 pages per call, split larger files with split_pdf first — which names an alternative sibling and the condition that selects it. It does not explicitly say when to prefer pdf_to_txt or image_to_text over OCR, so it falls short of full routing guidance.

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.