Skip to main content
Glama

redact_text

Detect and replace personally identifiable information (PII) in text with labeled placeholders to protect privacy before logging or sharing.

Instructions

Redact personally identifiable information (PII) from text.

Detects and replaces PII entities using NER and pattern matching.
Covers email addresses, phone numbers, full names, physical addresses,
credit card numbers, national ID numbers (UK NI, US SSN), dates of birth,
and IP addresses. Replacements use labelled placeholders so the structure
of the text is preserved for downstream processing.

Use before logging user input, storing support tickets, or sharing data
with third parties.

Args:
    text: Text containing PII to redact. Handles mixed content including
          structured data embedded in natural language.

Returns:
    redacted: Text with PII replaced by [REDACTED_TYPE] placeholders.
    entities: List of detected entities, each with:
        type: Entity type (EMAIL, PHONE, NAME, ADDRESS, CREDIT_CARD, etc.).
        original: The original value that was redacted.
        start, end: Character positions in the original text.
    entity_count: Total number of PII entities found and redacted.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
textYes
Behavior4/5

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

No annotations provided, so the description carries the full burden. It details detection methods (NER and pattern matching), covers a comprehensive list of PII types, and describes replacement style (labelled placeholders). However, it lacks discussion of limitations, performance, or error handling.

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 description is well-structured with sections for use cases and return values. It is informative without being verbose, though the Args and Returns sections are slightly redundant given the prose.

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?

Given the moderate complexity and lack of output schema, the description adequately covers functionality, usage, and return values. It does not mention concurrency, rate limits, or privacy, but is complete for its purpose.

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%, but the description compensates by explaining the 'text' parameter: 'Text containing PII to redact. Handles mixed content including structured data embedded in natural language.' This adds meaning beyond the schema.

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 description clearly states the function: redact PII from text. The verb 'redact' is specific, and the resource 'text' is explicit. It distinguishes from sibling tools, which are unrelated (e.g., validate_email, ssl_check).

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?

The description explicitly suggests use cases: 'before logging user input, storing support tickets, or sharing data with third parties.' This provides clear guidance on when to use, though it does not mention alternatives or when not to use.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ForeverTools/kiprio-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server