Skip to main content
Glama

Mask Korean personal data

kr_mask_pii
Read-onlyIdempotent

Mask Korean personal data before you store, log or share it. Text mode finds and masks resident registration numbers (900101-1******), phone numbers (010--5678), emails (ab@x.com) and 16-digit card numbers inside free text. Item mode masks given values by kind, including names (홍*동). Nothing is stored or logged.

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": "kr_mask_pii"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoFree text to scan (up to 100,000 characters)
itemsNoValues with a known kind (up to 1000)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered by structured data. The description adds one genuinely new behavioral claim, "Nothing is stored or logged", plus evidence that masking is partial and format-preserving (fixed-length asterisk runs). It does not say how detected entities are surfaced or what happens on ambiguous matches, so it adds moderate rather than rich context.

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 sentences, front-loaded with the action and the reason to use it, then mode-by-mode behavior, then the privacy guarantee. Every clause carries information; the inline masked examples communicate the transformation far more compactly than prose would.

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?

There is no output schema, and the description compensates by showing the shape of masked values for each entity type, which is the main thing an agent needs to reason about results. The remaining gap is structural: it never states that both parameters are optional, whether at least one is required, or what the response contains beyond the masked string.

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?

With 100% schema description coverage the baseline is 3, and the description earns above that by explaining the semantic difference between the two optional parameters: `text` performs automatic detection inside free text, while `items` masks caller-supplied values whose `kind` is already known. It also hints that names are only reachable via item mode, since the item enum omits card numbers despite text mode detecting them.

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 opens with a specific verb and resource ("Mask Korean personal data") and then enumerates the two operating modes with concrete masked-output examples for RRN, phone, email, card numbers and names. An agent can immediately tell this is a redaction tool rather than a formatter, but it never names a sibling (e.g. kr_phone_format or kr_name_split) to sharpen the boundary for related transformations.

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?

"before you store, log or share it" gives a clear triggering context, and the text-vs-item split implicitly routes the agent: free text goes to `text`, values with a known kind go to `items`. There are no explicit exclusions or a stated fallback when neither sibling redaction path applies, which keeps it short of a 5.

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.