ncloud-mcp-server

ncloud_create_metrics_group

Create a Cloud Insight rule template to group monitored metrics and set thresholds, conditions, and event levels for a target Naver Cloud product.

Instructions

Create a new Cloud Insight rule template (감시 항목 그룹 / metrics group).

Input Schema

TableJSON Schema

Name	Required	Description
`prodKey`	Yes	Product key (cw_key) for the target service
`prodType`	No	Product type: system (Ncloud product) or custom (Custom Schema)
`groupDesc`	No	Description (<= 300 chars)
`groupName`	Yes	Name of the metrics group (1-100 chars)
`temporaryGroup`	No	true: create the Event Rule without creating a metrics group (default false)
`metricsGroupItems`	Yes	Metric items (at least one)

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedv2.0.1Oct 7, 2026

addedInput schema / properties / groupDesc

Added value: +{
+  "description": "Description (<= 300 chars)",
+  "type": "string"
+}

changedInput schema / properties / groupName / description

Previous value: -"Name of the metrics group"New value: +"Name of the metrics group (1-100 chars)"

removedInput schema / properties / metricList

Removed value: -{
-  "description": "List of metric configurations",
-  "items": {
-    "additionalProperties": false,
-    "properties": {
-      "aggregation": {
-        "description": "Aggregation type",
-        "enum": [
-          "AVG",
-          "MIN",
-          "MAX",
-          "SUM",
-          "COUNT"
-        ],
-        "type": "string"
-      },
-      "condition": {
-        "description": "Threshold condition",
-        "enum": [
-          "GT",
-          "GTE",
-          "LT",
-          "LTE",
-          "EQ"
-        ],
-        "type": "string"
-      },
-      "duration": {
-        "description": "Duration in minutes before triggering",
-        "type": "number"
-      },
-      "eventLevel": {
-        "description": "Event severity level",
-        "enum": [
-          "CRITICAL",
-          "WARNING",
-          "INFO"
-        ],
-        "type": "string"
-      },
-      "metricGroupItemId": {
-        "description": "Metric item ID",
-        "type": "string"
-      },
-      "threshold": {
-        "description": "Threshold value",
-        "type": "number"
-      }
-    },
-    "required": [
-      "metricGroupItemId",
-      "condition",
-      "threshold",
-      "duration",
-      "eventLevel"
-    ],
-    "type": "object"
-  },
-  "type": "array"
-}

addedInput schema / properties / metricsGroupItems

Added value: +{
+  "description": "Metric items (at least one)",
+  "items": {
+    "additionalProperties": false,
+    "properties": {
+      "calculation": {
+        "description": "Aggregation of the metric",
+        "enum": [
+          "COUNT",
+          "SUM",
+          "MAX",
+          "MIN",
+          "AVG"
+        ],
+        "type": "string"
+      },
+      "condition": {
+        "description": "Threshold operator (LT, LE, EQ, GE, GT)",
+        "enum": [
+          "LT",
+          "LE",
+          "EQ",
+          "GE",
+          "GT"
+        ],
+        "type": "string"
+      },
+      "desc": {
+        "description": "Metric description",
+        "type": "string"
+      },
+      "dimensions": {
+        "description": "Dimension filters, e.g. [{dim:\"type\", val:\"svr\"}]",
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "dim": {
+              "description": "Dimension name defined in the schema (e.g. \"type\")",
+              "type": "string"
+            },
+            "val": {
+              "description": "Dimension value (e.g. \"svr\")",
+              "type": "string"
+            }
+          },
+          "required": [
+            "dim",
+            "val"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "duration": {
+        "description": "Duration (>= 1)",
+        "type": "number"
+      },
+      "eventLevel": {
+        "description": "Event level",
+        "enum": [
+          "INFO",
+          "WARNING",
+          "CRITICAL"
+        ],
+        "type": "string"
+      },
+      "metric": {
+        "description": "Metric name (e.g. avg_cpu_used_rto)",
+        "type": "string"
+      },
+      "metricGroupItemId": {
+        "description": "Metric group item ID (when updating an existing item)",
+        "type": "string"
+      },
+      "threshold": {
+        "description": "Threshold value",
+        "type": "number"
+      }
+    },
+    "required": [
+      "metric",
+      "eventLevel",
+      "condition",
+      "calculation",
+      "duration",
+      "threshold"
+    ],
+    "type": "object"
+  },
+  "minItems": 1,
+  "type": "array"
+}

addedInput schema / properties / prodType

Added value: +{
+  "description": "Product type: system (Ncloud product) or custom (Custom Schema)",
+  "enum": [
+    "system",
+    "custom"
+  ],
+  "type": "string"
+}

addedInput schema / properties / temporaryGroup

Added value: +{
+  "default": false,
+  "description": "true: create the Event Rule without creating a metrics group (default false)",
+  "type": "boolean"
+}

changedInput schema / required

Previous value: -[
-  "prodKey",
-  "groupName",
-  "metricList"
-]New value: +[
+  "prodKey",
+  "groupName",
+  "metricsGroupItems"
+]

First observedv1.10.1Jul 29, 2026

TDQS

B3.1/5.0

Behavior2/5

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

The only annotation is destructiveHint=false, which alone does not disclose much, and the description adds nothing beyond it. It never explains that this persists a new resource, what the temporaryGroup flag changes behaviorally, what is required to succeed, or any side effects — the full behavioral burden falls on the description and is unmet.

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?

A single front-loaded sentence with the verb first and zero waste; the parenthetical alias adds disambiguation rather than filler.

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?

The rich, fully described schema covers the input side and there is no output schema to explain, so the description need not detail return values. However, for a create-mutation tool with a nested item array and only a destructiveHint annotation, the description is thin on the behavioral and routing context an agent needs.

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%, so all six parameters (including the nested metricsGroupItems fields) are already documented in the schema. The description adds no parameter meaning beyond restating the resource name, so the baseline of 3 applies.

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 pairs a specific verb ("Create") with a clear resource ("Cloud Insight rule template / metrics group"), and the bilingual alias clarifies the domain term. It stops short of distinguishing itself from the sibling create/update metrics-group tools or explaining the rule-template wording, but an agent can identify the operation unambiguously.

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?

There is no when-to-use guidance, no prerequisites, and no mention of alternatives such as ncloud_update_metrics_group or ncloud_get_metrics_group. The agent must infer the usage context solely from the name.

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

Deploy Server

ncloud_create_metrics_group

Instructions

Input Schema

Schema Changelog

TDQS

Other Tools