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

io.github.ryanmat/logicmonitor

by ryanmat

capacity_plan

Read-onlyIdempotent

Forecast when device metrics will cross a capacity threshold by analyzing historical trends, seasonality, and change points to return breach ETAs and hours remaining.

Instructions

Composite capacity planning: reads each instance once through analyze_metric to classify its trend, detect seasonality and change points, and forecast when it crosses threshold (default 90). Summary rows carry each forecast method's breach_eta (epoch seconds) and hours_until_breach per datapoint.

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": "capacity_plan"
  }
}

Input Schema

NameRequiredDescriptionDefault
device_idNoDevice ID
thresholdNoLevel each forecast reaches for, in the datapoint's unit (default: 90)
datasourceNoFilter to a specific datasource name
hours_backNoHours of historical data (default: 168 = 1 week)
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.
warningsNo
device_idYes
thresholdYesThe level each forecast must reach.
hours_backYesHours of history each read covers.
datasourcesNoFull: up to five datasources and three instances each.
device_nameYes
detail_levelYes
forecast_summaryNoSummary: one headline row per datapoint read.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 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"
      -}
    • addedInput schema / properties / threshold
      Added value: +{
      +  "default": 90,
      +  "description": "Level each forecast reaches for, in the datapoint's unit (default: 90)",
      +  "type": "number"
      +}
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "datasources": {
      +      "description": "Full: up to five datasources and three instances each.",
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "datasource": {
      +            "type": "string"
      +          },
      +          "instances": {
      +            "items": {
      +              "additionalProperties": false,
      +              "properties": {
      +                "analysis": {
      +                  "description": "analyze_metric's trend, seasonality, change points and forecast; null when the read failed.",
      +                  "type": [
      +                    "object",
      +                    "null"
      +                  ]
      +                },
      +                "analysis_error": {
      +                  "type": "string"
      +                },
      +                "instance": {
      +                  "type": "string"
      +                }
      +              },
      +              "required": [
      +                "instance",
      +                "analysis"
      +              ],
      +              "type": "object"
      +            },
      +            "type": "array"
      +          }
      +        },
      +        "required": [
      +          "datasource",
      +          "instances"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "detail_level": {
      +      "enum": [
      +        "summary",
      +        "full"
      +      ],
      +      "type": "string"
      +    },
      +    "device_id": {
      +      "type": "integer"
      +    },
      +    "device_name": {
      +      "type": "string"
      +    },
      +    "forecast_summary": {
      +      "description": "Summary: one headline row per datapoint read.",
      +      "items": {
      +        "additionalProperties": false,
      +        "properties": {
      +          "breach_eta": {
      +            "additionalProperties": false,
      +            "description": "Epoch seconds each method reaches the threshold.",
      +            "properties": {
      +              "holt_winters": {
      +                "type": [
      +                  "number",
      +                  "null"
      +                ]
      +              },
      +              "linear": {
      +                "type": [
      +                  "number",
      +                  "null"
      +                ]
      +              }
      +            },
      +            "required": [
      +              "linear",
      +              "holt_winters"
      +            ],
      +            "type": "object"
      +          },
      +          "datapoint": {
      +            "type": "string"
      +          },
      +          "datasource": {
      +            "type": "string"
      +          },
      +          "hours_until_breach": {
      +            "additionalProperties": false,
      +            "properties": {
      +              "holt_winters": {
      +                "type": [
      +                  "number",
      +                  "null"
      +                ]
      +              },
      +              "linear": {
      +                "type": [
      +                  "number",
      +                  "null"
      +                ]
      +              }
      +            },
      +            "required": [
      +              "linear",
      +              "holt_winters"
      +            ],
      +            "type": "object"
      +          },
      +          "instance": {
      +            "type": "string"
      +          },
      +          "status": {
      +            "description": "Why no forecast was made.",
      +            "type": "string"
      +          },
      +          "trend": {
      +            "description": "The trend section's label.",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "datasource",
      +          "instance",
      +          "datapoint"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    },
      +    "hours_back": {
      +      "description": "Hours of history each read covers.",
      +      "type": "integer"
      +    },
      +    "portal": {
      +      "description": "The portal the call ran against, in multi-portal mode.",
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "threshold": {
      +      "description": "The level each forecast must reach.",
      +      "type": "number"
      +    },
      +    "warnings": {
      +      "items": {
      +        "type": "string"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "device_id",
      +    "device_name",
      +    "hours_back",
      +    "threshold",
      +    "detail_level"
      +  ],
      +  "type": "object"
      +}
  2. First observedv4.2.0

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), so the bar is lower; the description still adds real context by disclosing that it reads each instance once through analyze_metric (implying per-instance cost and a composite multi-call path) and that summary rows carry breach_eta and hours_until_breach. It does not mention latency, rate limits, or pagination, keeping it short of 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.

Conciseness4/5

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

Two dense sentences, front-loaded with the composite operation and then the output fields; nothing is padding. The phrasing is jargon-heavy ('breach_eta', 'per datapoint') but each clause carries information.

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

Completeness3/5

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

An output schema exists, so return values need not be explained, and annotations cover the safety profile. However, with six optional parameters (including an unexplained all-devices default and a summary/full detail toggle whose cost impact is unstated), the definition leaves an agent guessing about scope and output volume.

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 baseline is 3; the schema already defines threshold as the level forecasts reach, in the datapoint's unit, with default 90. The description restates the threshold default without adding format or behavioral detail (e.g., how detail_level changes output size, or what happens when no device filter is supplied).

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?

The description names a specific capability — composite capacity planning that classifies trend, detects seasonality/change points, and forecasts threshold breach — which is concrete and distinguishable from a plain metric read. It positions analyze_metric as an internal building block rather than naming a sibling to prefer for a different use case, so differentiation is implicit rather than explicit.

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?

'Composite capacity planning' plus the default threshold of 90 implies a capacity-planning scenario, but there is no explicit statement of when to choose this over analyze_metric or correlate_metrics, and no preconditions or exclusions. Usage must be inferred from the described behavior.

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