Skip to main content
Glama

eu_synthetic_data_masker

Read-onlyIdempotent

[Format-preserving synthetic data generator. Deterministic synthesis, read-only, side-effect free]. Generates mathematically valid European synthetic mock records (valid Codice Fiscale format, checksum-valid IBANs, realistic names, companies, and phone numbers) to completely replace real personal datasets under GDPR Recital 26. Usage: Use this tool to anonymize tabular/JSON training corpora, test datasets, and staging databases with format-faithful synthetic data. Returns: JSON object with { recordCount: number, fieldsProcessed: array, syntheticData: array, gdprRecital26Compliant: boolean, irreversibleAnonymization: boolean }.

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": {
      "records": "<records>"
    },
    "name": "eu_synthetic_data_masker"
  }
}

Input Schema

NameRequiredDescriptionDefault
localeNoTarget cultural locale (default: IT)
recordsYesArray of raw tabular/JSON records to be masked
fieldsToMaskNoSpecific field names to replace with synthetic mock values

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and idempotentHint=true, so 'read-only, side-effect free' is partly redundant, but the description adds genuine behavioral claims: deterministic synthesis, irreversible anonymization, a GDPR Recital 26 compliance flag, and format-preserving output with valid checksums. It does not discuss limits such as input size limits or handling of unsupported locales, but it goes well beyond what the annotations supply.

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 front-loaded with the core capability, then segmented into Usage and Returns blocks, which makes it easy to scan. The bracketed opening tag repeats safety traits already covered by annotations, a minor bit of waste in an otherwise tight structure.

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?

With no output schema, the description usefully enumerates the return shape (recordCount, fieldsProcessed, syntheticData, gdprRecital26Compliant, irreversibleAnonymization), so an agent knows what comes back. It remains silent on pass-through behavior for unmasked fields and on any size or performance limits, which are the main remaining gaps for a data-transformation 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?

Schema description coverage is 100%, so all three parameters (locale, records, fieldsToMask) are already documented in the schema, making baseline 3 appropriate. The description implies locale-specific formats but adds no meaning about how fieldsToMask interacts with records, for example whether unspecified fields pass through unchanged.

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 states a specific verb and resource: generating format-preserving European synthetic mock records (Codice Fiscale, checksum-valid IBANs, names, companies, phones) to replace real personal data. It is clear what the tool produces, though it never names the closely related eu_pii_scrubber_anonymizer sibling, so the agent must infer the distinction between synthesizing new values and scrubbing existing ones.

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 Usage line gives concrete use cases: anonymizing tabular/JSON training corpora, test datasets, and staging databases. However, it offers no when-not guidance and no explicit alternative, which matters here because eu_pii_scrubber_anonymizer appears to address the same anonymization job with a different mechanism.

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