Skip to main content
Glama
Sign In
ai-secure-by-design

ai-secure-by-design

by ankush1982
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Scan text for secrets and personal data

sbd_scan_text
Read-onlyIdempotent

Scan proposed text for hardcoded secrets and personal data before writing it, with sensitive snippets masked in findings.

Instructions

Scan proposed file content for hardcoded secrets and literal personal data before writing it. Snippets in findings are masked.

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": "sbd_scan_text"
  }
}

Input Schema

NameRequiredDescriptionDefault
textYes
filenameNoUsed for allow-listing lockfiles and fixtures, and in findings.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive, closed-world behavior, so the safety profile is covered. The description adds genuinely new behavior beyond them: findings come back with masked snippets, meaning the tool does not echo the secret back verbatim. It does not say whether the scan blocks a write or is advisory only, which leaves a meaningful gap for a pre-write gate.

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?

Two sentences, no filler, with the action and scope front-loaded and the masking note placed after it as secondary detail. Nothing here restates the title or wastes tokens.

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?

With no output schema, the description is the only source of return-value information, yet it only hints at "findings" with masked snippets. Severity levels, category/rule identifiers, and whether an empty result means clean are all unstated, which matters for an agent that must decide whether to proceed with a write based on the response.

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 50%: filename is documented (allow-listing lockfiles/fixtures), while text has no schema description at all. "Proposed file content" weakly implies text is raw content rather than a path, and the 2 MB ceiling is not surfaced, so the description only partially compensates for the undocumented required parameter.

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?

"Scan proposed file content for hardcoded secrets and literal personal data" gives a specific verb (scan), a specific resource (text content), and two named detection categories. The phrase "before writing it" pins the tool's place in the workflow and implicitly separates it from broader siblings like sbd_check or sbd_review_diff, though no sibling is named explicitly.

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?

The temporal trigger "before writing it" tells the agent exactly when to reach for this tool: pre-write validation of content it is about to persist. What is missing is an explicit exclusion, e.g. that this only covers literal patterns and that richer review belongs to sbd_review_diff, so the agent must infer the sibling boundary.

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