Skip to main content
Glama

Redact personal data from a PDF

redact_pdf
Idempotent

Finds IDs, bank accounts, cards, phone numbers, emails, names and addresses and really redacts them: nothing is left under the black box. Returns a link to download the result (kept about an hour). Credits on paid plans: 3 per page.

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": {
      "files": "<files>"
    },
    "name": "redact_pdf"
  }
}

Input Schema

NameRequiredDescriptionDefault
langNoLanguage. Language of the texts the tool adds. Values: 'es' = Spanish; 'en' = Englishes
modeNoResult Values: 'tachar' = Redact them (permanent); 'marcar' = Just mark them, to reviewtachar
filesYesInput files (.pdf). Each one is a public http(s) URL, or an object with `url`, or with `name` and `content_base64` (small files only: up to 20 MB in total).
termsNoOther words or names, separated by commas. e.g. Ana Ruiz, Project Phoenix
categoriesNoWhat to redact Values: 'dni' = Spanish ID (DNI, NIE); 'iban' = Bank accounts (IBAN); 'tarjeta' = Cards; 'telefono' = Phone numbers; 'email' = Emails; 'nombre' = Names; 'direccion' = Addresses

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior4/5

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

Beyond the annotations it discloses two facts the agent cannot infer elsewhere: the download link expires in about an hour, and paid plans are charged 3 credits per page. It also clarifies that redaction is irreversible ('nothing is left under the black box'), which complements rather than contradicts destructiveHint=false since the input file is not destroyed.

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?

Two short sentences, front-loaded with the capability and immediately followed by the result format and cost. Every clause carries information: what is found, what is truly removed, what is returned, how long it lasts, and what it costs.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Return value is covered (download link, ~1 hour retention) and cost is covered, which matters since there is no output schema. However, the presence of a job_status sibling makes it unclear whether this call returns the link synchronously or requires polling; the description implies immediate return without saying so, leaving an execution-model gap for a multi-file, credit-charging operation.

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

Parameters3/5

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

Schema coverage is 100%, so all five parameters (lang, mode, files, terms, categories) are already documented in the schema. The description's enumeration of entity types loosely mirrors the categories enum but adds no syntax, defaults, or edge-case meaning beyond it, so the baseline 3 applies.

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 ('redacts' a PDF) plus the exact entity classes it targets, so the agent knows precisely what the tool does. The phrase 'really redacts them: nothing is left under the black box' further distinguishes it from a cosmetic overlay like watermark_pdf.

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?

Usage is implied by the name and the category list, and the description hints at a review-first workflow ('mode: marcar' exists in the schema, not the description). It never states when to pick this over siblings such as watermark_pdf or ocr_pdf, nor any preconditions beyond public URL / 20 MB limits that already live in the schema.

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.

Resources