Skip to main content
Glama

scan_data_map

Scan code to identify personal data collected and third-party services it is sent to, with evidence at file:line plus data fields and features.

Instructions

Call to see what personal data the code collects and which third-party services it sends data to. Scans the whole codebase (current folder if no config) and returns third-party services (company, country, purpose, evidence file:line), personal-data fields, and a feature list. Facts only; no judgment.

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": "scan_data_map"
  }
}

Input Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It discloses the scan scope (whole codebase, current folder fallback) and specifies the returned data shape in detail, including evidence file:line and the "facts only; no judgment" caveat. However, it omits whether the scan is read-only, expected runtime, or any permission requirements, which are important for an agent invoking a codebase-wide scan.

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 three front-loaded sentences with no wasted wording. The purpose comes first, followed by scan behavior and output contents, then a clear scope caveat. It is appropriately sized for a zero-parameter tool.

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?

No output schema exists, so the description usefully spells out the return contents: third-party services with company, country, purpose, and evidence file:line, plus personal-data fields and a feature list. The scan scope and fallback folder behavior are also covered. Minor gaps remain, such as whether the scan is read-only and how large codebases are handled, but the core invocation context is complete.

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?

The tool takes zero parameters, so the baseline is 4. No parameter semantics need to be conveyed, and the description does not introduce confusing parameter-like details.

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: it scans the codebase to identify personal data collection and third-party service data flows. The phrase "whole codebase" implicitly contrasts with the sibling scan_changes, but no sibling is explicitly named or differentiated.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description opens with "Call to see..." but gives no conditions for when to use this tool versus scan_changes, audit, get_checklist, or get_policies. There are no when-not-to-use cases or prerequisites stated, leaving the agent to infer selection.

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