Skip to main content
Glama

Redact PDF

redact_pdf
Destructive

Remove text for real, not just cover it: name the exact text to remove, or describe it ("all names, emails and account numbers") and FynePDF finds it. The result is checked: if any of the text can still be found, nothing is returned. The original file is kept.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "redact_pdf"
  }
}

Input Schema

NameRequiredDescriptionDefault
fileNoA file the person attached in ChatGPT (filled in by ChatGPT).
findNoWhat to remove, in words (uses AI to find it).
textNo
file_idNoA FynePDF file_id from upload_file, import_file_from_url or an earlier tool.
file_urlNoA public link to the file.
match_caseNo
library_file_idNoA file from the person's FynePDF Library (from list_library_files).
remove_metadataNo

Output Schema

NameRequiredDescriptionDefault
cardNo
filesYes
foundNo
stepsYes
job_idYes
statusYes
creditsYes
messageYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed14 schema fields changed
    • removedOutput schema / properties / files / items / properties / bytes / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / files / items / properties / bytes / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / files / items / properties / download_url / anyOf
      Removed value: -[
      -  {
      -    "type": "string"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / files / items / properties / download_url / type
      Added value: +[
      +  "string",
      +  "null"
      +]
    • removedOutput schema / properties / files / items / properties / pages / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / files / items / properties / pages / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / steps / items / properties / bytes_after / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / steps / items / properties / bytes_after / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / steps / items / properties / bytes_before / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / steps / items / properties / bytes_before / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / steps / items / properties / pages_after / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / steps / items / properties / pages_after / type
      Added value: +[
      +  "number",
      +  "null"
      +]
    • removedOutput schema / properties / steps / items / properties / pages_before / anyOf
      Removed value: -[
      -  {
      -    "type": "number"
      -  },
      -  {
      -    "type": "null"
      -  }
      -]
    • addedOutput schema / properties / steps / items / properties / pages_before / type
      Added value: +[
      +  "number",
      +  "null"
      +]
  2. First observed

TDQS

A3.7/5.0
Behavior4/5

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

Beyond the destructiveHint=true annotation, the description discloses a verification guarantee (if any target text remains findable, nothing is returned) and that the original file is preserved. That is genuinely useful behavioral context. It does not say what the successful response contains or whether a new file_id is produced, though an output schema covers returns.

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?

Three short sentences, front-loaded with the core differentiator and the mode choice, then the verification guarantee, then the source-file safety note. No filler.

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?

The output schema relieves the description of explaining return values, and the destructive nature is covered by annotations. However, for a tool with four mutually exclusive ways to specify a file plus match_case and remove_metadata, the absence of any guidance on which file source to use is a notable gap.

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?

The description adds real meaning to two parameters by contrasting naming exact strings versus describing them in words, which maps onto the text/find split. With 63% schema coverage it leaves match_case, remove_metadata, and the four different file-input parameters (file, file_id, file_url, library_file_id) unexplained.

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?

"Remove text for real, not just cover it" states a specific verb and resource, and the contrast with merely covering text implicitly separates it from overlay-style siblings like stamp_pdf or smart_edit. No sibling is named, so an agent must infer the boundary, but the mechanism is unambiguous.

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 conveys the two supported modes (exact text list vs. a natural-language description) and the intent of true removal, which implies when to reach for it. It never states when not to use it or explicitly names alternatives such as stamp_pdf for visual masking, leaving routing partly to inference.

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.