Skip to main content
Glama

ml_train_incident_classifier

Train the incident classification ML solution in ServiceNow, optionally as a background job or dry run, so predictions improve with updated data.

Instructions

Trigger training of the incident classification ML solution. [Write]

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": "ml_train_incident_classifier"
  }
}

Input Schema

NameRequiredDescriptionDefault
asyncNoRun as a background job and return a job_id at once. Poll it with get_job. Calls that take longer than about 20 seconds switch to a job on their own.
dry_runNoResolve the solution definition without submitting a training job (default false)
solution_nameNoML solution name (default auto-detect)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv5.0.1
    • addedInput schema / properties / async
      Added value: +{
      +  "description": "Run as a background job and return a job_id at once. Poll it with get_job. Calls that take longer than about 20 seconds switch to a job on their own.",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / dry_run
      Added value: +{
      +  "description": "Resolve the solution definition without submitting a training job (default false)",
      +  "type": "boolean"
      +}
  2. First observedv1.0.2

TDQS

C2.8/5.0
Behavior2/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true, idempotentHint=false, and destructiveHint=false; the description's only added signal is the '[Write]' marker, which merely restates readOnlyHint=false. It omits genuinely useful behavior for a training trigger: that a job is launched and takes time, that repeated calls start redundant training runs (non-idempotent), and any cost or concurrency implications.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short, front-loaded sentences with no filler, but the '[Write]' token is redundant with the annotations and consumes part of an already minimal description. It is concise at the cost of being under-specified rather than economical.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

This is a mutating, potentially long-running, non-idempotent trigger with no output schema, yet the description says nothing about what happens after the call (job submission, model artifact creation) or whether existing models are replaced. The async caveats live only in the schema, leaving the description too thin for the tool's complexity.

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%, and the schema text for async, dry_run, and solution_name is detailed (including the get_job polling hint and the ~20 second fallback). The description adds no parameter meaning beyond that, which is the expected baseline when the schema does the work.

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 a specific verb (trigger training) and a specific resource (the incident classification ML solution), which distinguishes it from the sibling trainers for anomaly detection and change risk. It lacks only an explicit pointer to those alternatives, so it stops short of a 5.

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 gives no when-to-use guidance: no prerequisites (does a solution definition need to exist first?), no note on when retraining is warranted, and no mention of when to prefer the anomaly or change-risk trainers. Usage must be inferred from the verb alone.

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