Skip to main content
Glama
surinch-db-guard

surinch-db-guard

sensitive_masking_scan

Classify sensitive columns and generate masking VIEW SQL from DDL metadata for MySQL, PostgreSQL, or Doris, with a SHA-256 verifiable receipt and no row data reads.

Instructions

Metadata-only sensitive column classifier (L4/L3/L2) & deterministic masking VIEW SQL generator for MySQL/PostgreSQL/Doris DDL with SHA-256 verifiable receipt. Never reads row data.

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": {
      "ddl": "<ddl>"
    },
    "name": "sensitive_masking_scan"
  }
}

Input Schema

NameRequiredDescriptionDefault
ddlYesCREATE TABLE DDL metadata text (schema-only, no sample row values).
dialectNomysql
viewPrefixNoPrefix for generated masking VIEW names (alphanumeric + underscore).v_masked_

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.6/5.0
Behavior4/5

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

With no annotations, the description carries the full burden and does disclose key traits: it is metadata-only, never reads row data, masking is deterministic, and it emits a SHA-256 verifiable receipt. It stops short of stating whether generated SQL is executed or merely returned, and says nothing about permissions or side effects.

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?

A single dense, front-loaded sentence with no filler, and the key safety constraint ('never reads row data') is placed last for emphasis. The L4/L3/L2 labels and 'verifiable receipt' are unexplained jargon that costs some clarity.

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?

There is no output schema, so the description should explain what comes back. It names the artifacts (classification levels, masking VIEW SQL, receipt) but not their structure, field names, or whether SQL is returned as text, leaving a real gap for a 3-parameter generator 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 coverage is 67%, so the schema already documents ddl and viewPrefix well. The description reinforces the ddl constraint (metadata-only, no row values) and the dialect list, but adds no format or syntax guidance beyond what the schema provides, leaving the default-viewPrefix behavior undocumented.

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?

States specific verbs and resources: sensitive column classification (L4/L3/L2) plus masking VIEW SQL generation, scoped to MySQL/PostgreSQL/Doris DDL. An agent can tell this is a DDL-metadata analyzer rather than a governance check or a read-only review, though it never names the siblings it differs from.

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?

Usage is only implied: you supply CREATE TABLE DDL and get classification plus masking VIEW SQL. There is no explicit when-to-use, when-not-to-use, or routing statement relative to ddl_governance_check or sql_readonly_review, so the agent must infer the boundary from the input type.

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