Skip to main content
Glama
Sign In

X3 Compliance

by io.github.x3allamerican
OverviewDiscussionsAdmin

DOT random drug and alcohol testing: how many, and a fair draw

dot_random_testing
Read-onlyIdempotent

FMCSA random testing under 49 CFR 382.305: the year's minimum tests from the average pool (50% drug, 10% alcohol for 2026), how many to select this period to stay on pace, and optionally an unbiased random selection from a list of driver IDs (use employee numbers, never names or SSNs), with a pool fingerprint.

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": {
      "poolSizes": "<poolSizes>",
      "periodsPerYear": "<periodsPerYear>"
    },
    "name": "dot_random_testing"
  }
}

Input Schema

NameRequiredDescriptionDefault
seedNoOptional seed to make the draw reproducible for an auditor
poolIdsNoOptional: driver IDs to draw from now
poolSizesYesDrivers in the pool for each period so far this year, including the current one
drugTestsDoneNoDrug tests completed in earlier periods
periodsPerYearYes4 for quarterly, 12 for monthly
alcoholTestsDoneNoAlcohol tests completed in earlier periods

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, closed-world, and non-destructive, so the safety profile is covered. The description adds real context beyond that: the draw is unbiased, a seed makes it reproducible for an auditor, a pool fingerprint is produced, and IDs must be employee numbers rather than names or SSNs — a privacy constraint the schema does not carry.

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 sentence, but it is front-loaded with the regulatory citation and the primary computation before the optional draw. The parenthetical rate figures and the SSN warning both earn their place; only the triple-clause packing keeps it from being maximally scannable.

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 still conveys what comes back: the year's minimum test counts, the per-period selection number, the optional drawn IDs, and a pool fingerprint. For a six-parameter calculation tool with full schema coverage and strong annotations, that covers what an agent needs to call it correctly.

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?

Schema coverage is 100%, so the baseline is 3, but the description earns an increment by explaining why the seed matters (auditor reproducibility) and constraining the contents of poolIds to employee numbers. It does not restate poolSizes or periodsPerYear semantics, which the schema already handles well.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb-and-resource pair: computing FMCSA random-testing minimums under 49 CFR 382.305, period selection counts, and an optional random draw. It also pins the domain with the 50% drug / 10% alcohol rates for 2026, so an agent can tell this apart from the CFR-lookup and compliance siblings without opening the schema.

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?

It states the operating context clearly: use it to determine how many tests to select this period to stay on pace, with the draw as an explicitly optional add-on. There is no explicit 'do not use for X' or named alternative, but no sibling in the catalog overlaps this compute-plus-draw function, so the guidance is adequate without exclusions.

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

All X3 Compliance toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources