Skip to main content
Glama
@caelaralabs/mcp

@caelaralabs/mcp

caelara_agent_pii_redactor

Redact emails, phone numbers, SSNs, card numbers, IPs, API keys, and JWTs from text to safely screen agent input and output before processing or storage.

Instructions

[Agent Safety] Redact emails, phones, SSNs, cards (Luhn), IPs, API keys and JWTs Measured p50 11 ms, p95 15 ms (2026-11-21, benchmarks.caelaralabs.com). Calls https://agent.caelaralabs.com.

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": {
      "text": "<text>"
    },
    "name": "caelara_agent_pii_redactor"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYesText to redact

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.1

TDQS

B3.4/5.0
Behavior3/5

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

No annotations are supplied, so the description carries the full behavioral burden. It does add real context — Luhn validation for card numbers, concrete latency figures with a dated benchmark source, and the backend endpoint — but it never says what the call returns (redacted string vs. spans vs. counts), what placeholder format is used, or whether redaction is reversible, which are the details an agent most needs for a transform tool.

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?

Two compact sentences with the entity coverage front-loaded, which is exactly the information an agent needs first. The benchmark citation with date, percentile figures, and a URL is verifiable but borders on promotional clutter for a tool definition.

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 tool is simple (one string in), but there is no output schema, so the description must explain the return value — and it does not. An agent can call it correctly but cannot predict whether it gets back cleaned text, a list of detected spans, or a redaction count, which is a meaningful gap for a transform tool.

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?

There is a single required parameter with 100% schema description coverage ("Text to redact"), so the schema already does the work. The description adds no format hints, size limits, or encoding expectations beyond what the schema states, making the baseline 3 appropriate.

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?

The description leads with a specific verb ("Redact") and enumerates the exact entity classes covered — emails, phones, SSNs, cards with Luhn validation, IPs, API keys, JWTs — which makes the tool's scope unmistakable and clearly separates it from sibling scanners/validators. It stops short of a 5 because it never names or contrasts a sibling tool, leaving the agent to infer the boundary itself.

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 "[Agent Safety]" prefix implies this belongs to a safety/prompt-sanitization pipeline, and redaction of PII before further processing is implied by the verb. There is no explicit statement of when to call this versus e.g. the prompt injection scanner or output validator, and no prerequisites or exclusions are given.

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

Deploy Server

Other Tools