Skip to main content
Glama
io.github.ryanmat/logicmonitor

io.github.ryanmat/logicmonitor

by ryanmat

health_check

Read-onlyIdempotent

Resolves a device, reviews CPU, memory, and disk metrics, open alerts, and 30-day availability to assess overall device health.

Instructions

Composite health check: resolves a device, picks up to five of its datasources whose names mention CPU, memory or disk (drive, volume, filesystem), reads the first instance of each through analyze_metric (summary and anomalies over 24 hours), checks open alerts, and calculates 30-day availability. A device with none of those datasources gets an empty metrics list and a warning.

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": "health_check"
  }
}

Input Schema

NameRequiredDescriptionDefault
device_idNoDevice ID
device_nameNoDevice display name (used if device_id not provided)
detail_levelNoOutput detail level (default: summary)summary

Output Schema

NameRequiredDescriptionDefault
portalNoThe portal the call ran against, in multi-portal mode.
metricsNoFull: the first instance of each CPU, memory or disk datasource read.
warningsNo
device_idYes
device_nameYes
availabilityYescalculate_availability, 30 days.
detail_levelYes
active_alertsYesget_alerts, open, for the device.
datasource_countYesDatasources the device carries.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv5.0.1
    • removedInput schema / properties / summarize
      Removed value: -{
      -  "default": false,
      -  "description": "Append plain-English NL summary via IBM Granite (requires WATSONX_API_KEY)",
      -  "type": "boolean"
      -}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "active_alerts": {
      +      "description": "get_alerts, open, for the device.",
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "availability": {
      +      "description": "calculate_availability, 30 days.",
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "datasource_count": {
      +      "description": "Datasources the device carries.",
      +      "minimum": 0,
      +      "type": "integer"
      +    },
      +    "detail_level": {
      +      "enum": [
      +        "summary",
      +        "full"
      +      ],
      +      "type": "string"
      +    },
      +    "device_id": {
      +      "type": "integer"
      +    },
      +    "device_name": {
      +      "type": "string"
      +    },
      +    "metrics": {
      +      "description": "Full: the first instance of each CPU, memory or disk datasource read.",
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "analysis": {
      +            "description": "analyze_metric's summary and anomalies over 24 hours.",
      +            "type": "object"
      +          },
      +          "datasource": {
      +            "type": "string"
      +          },
      +          "instance": {
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "datasource",
      +          "instance",
      +          "analysis"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "portal": {
      +      "description": "The portal the call ran against, in multi-portal mode.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "warnings": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "device_id",
      +    "device_name",
      +    "detail_level",
      +    "datasource_count",
      +    "active_alerts",
      +    "availability"
      +  ],
      +  "type": "object"
      +}
  2. First observedv4.2.0

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already cover read-only, idempotent, non-destructive, and open-world, so the bar is lower, yet the description still adds substantial behavior: a hard cap of five datasources selected by name matching, only the first instance of each metric read, a 24-hour window for summaries/anomalies, and a 30-day availability window. It also discloses the edge case of a device with no matching datasources returning an empty metrics list plus a warning. It does not mention cost/latency of the composite fan-out or what happens when the device cannot be resolved at all.

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?

It is a single dense sentence, but it is front-loaded with the purpose and every clause carries new information about scope or behavior. It is slightly run-on and would scan better as a short list, but there is no filler.

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?

With an output schema present, return-value detail is unnecessary, and the description fully covers the aggregation logic and the empty-result edge case. The only meaningful gap for a multi-source composite is the failure mode when the device itself cannot be resolved, plus any indication of latency from fanning out to five datasources.

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 three parameters are documented there, including the device_id/device_name fallback and the detail_level enum with its default. The description only alludes to 'resolves a device' and does not add syntax, precedence, or format detail beyond the schema, so the baseline 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 opens with a specific label, 'Composite health check,' and then enumerates exactly what it aggregates: device resolution, up to five CPU/memory/disk datasources, first-instance reads via analyze_metric, open alerts, and 30-day availability. An agent can distinguish this from the atomic siblings like analyze_metric or calculate_availability without opening a schema.

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

Usage Guidelines3/5

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

The flow implies this is the one-shot aggregation tool and names analyze_metric as the underlying read path, so the agent can infer it is a wrapper over several atomic calls. However, it never explicitly says when to prefer this over calling analyze_metric, get_alerts, and calculate_availability individually, nor any when-not conditions.

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