Skip to main content
Glama

Condition monitoring triage — Atom

Condition monitoring triage

condition_monitoring_triage
Read-onlyIdempotent

Submit a condition-monitoring evidence manifest (baseline, monitoring/context/trending discipline, declared alert bands with readings, alarm triage record); get a deterministic TRIAGE_SOUND / TRIAGE_UNSOUND / INSUFFICIENT_EVIDENCE verdict across six sections, including computed reading-vs-band classification and action-band triage checks, with per-check evidence.

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": "condition_monitoring_triage"
  }
}

Input Schema

NameRequiredDescriptionDefault
assetNoAsset being monitored (e.g. MTR-101).
bandsNoAlert-band definition evidence.
alarmsNoAlarm triage record: {id, disposition: noise|watch|act, reasoning_recorded, recheck_interval_set, work_request_raised}.
contextNoReading-context evidence (load, ambient, speed).
baselineNoBaseline evidence (exists, known load, post-repair capture).
readingsNoDeclared readings: {parameter, value, watch_limit, warning_limit, action_limit}.
trendingNoTrending evidence (deltas, rate of change, repair annotations).
escalationNoEscalation and red-line evidence.
monitoringNoTechnique/route/instrument discipline evidence.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

The annotations already establish that the tool is read-only, idempotent, non-destructive and closed-world; the description adds substantive behavior beyond them by disclosing that evaluation is deterministic, spans six sections with computed reading-vs-band classification and action-band triage checks, and returns per-check evidence. It does not say how missing or partial evidence is handled beyond implying the INSUFFICIENT_EVIDENCE outcome.

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?

One dense sentence, front-loaded with the input manifest, then the verdict, then the supporting evidence; parentheses carry the component list without wasted prose.

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, and the description explains the verdict set, the six-section scope, and the per-check evidence return, which is most of what an agent needs. It does not clarify that every parameter is optional or how partial manifests are scored, a minor remaining gap for a nine-parameter evaluator.

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 100%, so the schema already documents each parameter, including the inline shapes for readings and alarms. The description adds grouping value by showing which manifest components map to the evaluation, but omits 'asset' and 'escalation' entirely and supplies no syntax beyond what the schema states; the baseline of 3 applies.

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 ('Submit a condition-monitoring evidence manifest') and states the exact output taxonomy ('TRIAGE_SOUND / TRIAGE_UNSOUND / INSUFFICIENT_EVIDENCE verdict across six sections'), which an agent can use to distinguish this from any generic validation or asset tool.

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 is clear about the context in which the tool applies: it consumes a full evidence manifest covering baseline, monitoring, context, trending, bands and alarms, and is used to obtain a triage verdict. It does not state when NOT to use it, nor whether the verdict can be obtained when the manifest is empty (zero required parameters), leaving that inference to the agent.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.