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

io.github.ryanmat/logicmonitor

by ryanmat

triage

Read-onlyIdempotent

Review recent LogicMonitor alerts in one call by analyzing statistics, clusters, noise, and changes, then count blast radius for up to three device clusters.

Instructions

Triage the alerts of the last hours_back hours in one call. Reads the alert window once through analyze_alerts for its statistics, clusters (by device, datasource and signature), noise and changes, then counts the blast radius of up to three device clusters, largest first. Each count row gives the devices reached as neighbors and as dependents, how many of them have a critical alert open, and how many devices' neighbors could not be read; a website cluster gets none. The clusters section lists the five largest clusters of each type with ten alert ids each, and changes the ten change and spike pairs of highest confidence; cluster_count, by_type and total_correlated count them all, and a narrower severity, device or window shows the rest. detail_level=full adds the devices each blast radius reached. Use analyze_alerts for bursts or a single section, and analyze_blast_radius for one device.

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": "triage"
  }
}

Input Schema

NameRequiredDescriptionDefault
deviceNoFilter by device name
group_idNoFilter by device group ID
severityNoFilter alerts by severity
hours_backNoHours to look back (default: 4)
detail_levelNoOutput detail level (default: summary)summary

Output Schema

NameRequiredDescriptionDefault
noiseYesanalyze_alerts 'noise'.
portalNoThe portal the call ran against, in multi-portal mode.
changesYesanalyze_alerts 'changes'.
clustersYesanalyze_alerts 'clusters'.
warningsNo
hours_backYesHours the alert window reaches back.
statisticsYesanalyze_alerts 'statistics'.
blast_radiusYesOne row per device cluster read, up to three.
detail_levelYes

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": {
      +    "blast_radius": {
      +      "description": "One row per device cluster read, up to three.",
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "affected_devices": {
      +            "description": "Full: each device reached, with its depth and open alerts.",
      +            "items": {
      +              "type": "object"
      +            },
      +            "type": "array"
      +          },
      +          "critical_alert_count": {
      +            "description": "Devices reached with a critical alert open.",
      +            "minimum": 0,
      +            "type": "integer"
      +          },
      +          "critical_path_devices": {
      +            "description": "Full: devices reached from two or more others.",
      +            "items": {
      +              "type": "object"
      +            },
      +            "type": "array"
      +          },
      +          "degraded_detail": {
      +            "description": "Present when an alert check failed; critical counts may be low.",
      +            "type": "string"
      +          },
      +          "dependent_count": {
      +            "description": "Devices reached at depth 2 and beyond.",
      +            "minimum": 0,
      +            "type": "integer"
      +          },
      +          "device": {
      +            "description": "The device's name, the cluster's key.",
      +            "type": "string"
      +          },
      +          "device_id": {
      +            "description": "The device the cluster's alerts share.",
      +            "type": "integer"
      +          },
      +          "neighbor_count": {
      +            "description": "Devices reached at depth 1.",
      +            "minimum": 0,
      +            "type": "integer"
      +          },
      +          "total_affected_devices": {
      +            "description": "Devices reached at any depth.",
      +            "minimum": 0,
      +            "type": "integer"
      +          },
      +          "unreadable_count": {
      +            "description": "Devices whose neighbors neither topology path answered.",
      +            "minimum": 0,
      +            "type": "integer"
      +          },
      +          "warning": {
      +            "description": "Present when unreadable_count is not 0.",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "device",
      +          "device_id",
      +          "total_affected_devices",
      +          "neighbor_count",
      +          "dependent_count",
      +          "critical_alert_count",
      +          "unreadable_count"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "changes": {
      +      "description": "analyze_alerts 'changes'.",
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "clusters": {
      +      "description": "analyze_alerts 'clusters'.",
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "detail_level": {
      +      "enum": [
      +        "summary",
      +        "full"
      +      ],
      +      "type": "string"
      +    },
      +    "hours_back": {
      +      "description": "Hours the alert window reaches back.",
      +      "type": "integer"
      +    },
      +    "noise": {
      +      "description": "analyze_alerts 'noise'.",
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "portal": {
      +      "description": "The portal the call ran against, in multi-portal mode.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "statistics": {
      +      "description": "analyze_alerts 'statistics'.",
      +      "type": [
      +        "object",
      +        "null"
      +      ]
      +    },
      +    "warnings": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "hours_back",
      +    "detail_level",
      +    "statistics",
      +    "clusters",
      +    "noise",
      +    "changes",
      +    "blast_radius"
      +  ],
      +  "type": "object"
      +}
  2. First observedv4.2.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnly, idempotent, non-destructive and open-world, so the safety profile is covered. The description adds genuinely useful behavior beyond that: result truncation caps (five clusters per type, ten alert ids each, ten change/spike pairs), the fact that aggregate counters still reflect everything, and what detail_level=full unlocks. It stops short of stating cost/latency implications of the multi-read composite, which keeps it from a 5.

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?

The purpose is front-loaded and every sentence carries information, but the second and third sentences are extremely long clause-chains that mix output-shape detail with operational guidance. Much of the middle content restates what the output schema already declares, so density comes at the cost of readability rather than pure economy.

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?

For a multi-section composite tool with an output schema, annotations and full schema coverage, the description is essentially complete: selection guidance, alternative tools, truncation behavior and detail_level effects are all present. The only minor redundancy is the verbose recounting of return fields that the output schema already defines.

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 adds real meaning: hours_back defines the alert window, severity/device act as narrowing filters that surface results beyond the truncation caps, and detail_level=full is concretely defined as adding the devices each blast radius reached. That is more than a restatement of the enum labels.

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 verb and resource ('Triage the alerts of the last hours_back hours in one call') and immediately decomposes the composite behavior into named sub-reads (analyze_alerts statistics, clustering by device/datasource/signature, blast-radius counts). It explicitly distinguishes itself from analyze_alerts and analyze_blast_radius, so an agent can select it without opening other schemas.

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

Usage Guidelines5/5

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

The final sentence gives an explicit routing rule: use analyze_alerts for bursts or a single section, and analyze_blast_radius for one device. It also states how to widen results ('a narrower severity, device or window shows the rest'), which tells the agent when this tool is the right reach versus a focused sibling.

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