Skip to main content
Glama

Скрыть персональные данные

redact_pdf

Скрывает персональные данные в PDF: находит и удаляет из файла (не просто закрашивает сверху) — под чёрными прямоугольниками текста больше нет. Без areas — ищет сам. file_url: публичный URL PDF-файла. kinds: что искать — passport, snils, inn, phone, email, card, account (счета физлиц); по умолчанию всё. words: свои слова — ФИО, адрес, название (каждое от 3 символов). areas: области вручную — [{"page": 1, "box": [x0, y0, x1, y1]}] долями страницы (например, из find_personal_data). clean: убрать скрытые данные файла — автора, свойства, комментарии, вложения (по умолчанию да). На сканах текста нет — сначала ocr_pdf или укажите areas.

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": "redact_pdf"
  }
}

Input Schema

NameRequiredDescriptionDefault
areasNo
cleanNo
kindsNo
wordsNo
file_urlYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.2/5.0
Behavior3/5

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

The description adds real behavioral context beyond the annotations: redaction is genuine content removal rather than a black box drawn on top, and clean defaults to stripping author, properties, comments and attachments. That is useful disclosure for an operation that permanently alters a document. However, it never says whether the original file is overwritten or a new file is produced, and the permanent removal of content sits somewhat uneasily with destructiveHint=false in the annotations, which the description does not reconcile.

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?

The definition is front-loaded with the core action and the crucial 'real deletion, not overlay' distinction, then walks parameters one per line in a predictable order. The only waste is the near-duplication between 'не просто закрашивает сверху' and 'под чёрными прямоугольниками текста больше нет', which restates the same guarantee.

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?

For a five-parameter mutation tool, all parameters, the default detection mode, the scan limitation and the sibling handoffs are covered, and an output schema exists so return values need no explanation. The remaining gap is operational: it does not say whether the source document is modified in place or a redacted copy is returned, which matters before an agent commits to the call.

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 does so for every parameter: file_url as a public URL, kinds with the concrete enumerated values (passport, snils, inn, phone, email, card, account) plus the all-by-default behavior, words with the 3-character minimum, areas with the exact object shape and the note that coordinates are fractions of the page, and clean with its default. This is meaning the schema cannot convey on its own.

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 first sentence gives a specific verb and resource ('Скрывает персональные данные в PDF') and immediately distinguishes the operation from a visual overlay by stating the text is actually removed ('не просто закрашивает сверху ... текста больше нет'). It also separates the tool from the sibling find_personal_data, which only locates data, so an agent can tell the two apart without opening either schema.

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?

It states the default mode explicitly ('Без areas — ищет сам') and names a concrete alternative for the failure case: on scans without a text layer, run ocr_pdf first or supply areas manually. It also points to find_personal_data as a source of area coordinates, implying a find-then-redact workflow. What is missing is an explicit statement of when to prefer find_personal_data alone (preview without modification) versus calling this tool.

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.