Phare

Create a maintenance window

create_maintenance_window

Schedule a maintenance window for monitors of the project, shown right away on the linked status pages. It starts at starts_at and ends at ends_at on its own, and its monitoring_mode sets what happens to the monitors meanwhile: pause pauses them, mute keeps checking them without incident alerts, normal only announces the maintenance.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "project_id": "<project_id>",
      "title": "<title>",
      "monitoring_mode": "<monitoring_mode>",
      "starts_at": "<starts_at>",
      "ends_at": "<ends_at>",
      "monitors": "<monitors>"
    },
    "name": "create_maintenance_window"
  }
}

Input Schema

Name	Required	Description
`tags`	No	Resource tags, made of lowercase letters, numbers, `.`, `_`, `:` and `-`. An organization can have up to 200 tags.
`title`	Yes	Maintenance window title
`ends_at`	Yes	Date and time when the maintenance window ends, with minute precision (seconds must be `00`). Must be after `starts_at` and within the next year.
`monitors`	Yes	List of monitor IDs linked to the maintenance window
`starts_at`	Yes	Date and time when the maintenance window starts, with minute precision (seconds must be `00`). Must be within the next year.
`project_id`	Yes	ID of the project to act on, see whoami
`description`	No	Description of the maintenance window
`status_pages`	No	List of status page IDs linked to the maintenance window
`monitoring_mode`	Yes	Monitoring mode during maintenance

Output Schema

Name	Required	Description
`id`	No	Maintenance window ID
`tags`	No	Resource tags, made of lowercase letters, numbers, `.`, `_`, `:` and `-`. An organization can have up to 200 tags.
`state`	No	Maintenance window state
`title`	No	Maintenance window title
`ends_at`	No	Date and time when the maintenance window ends, with minute precision (seconds must be `00`). Must be after `starts_at` and within the next year.
`monitors`	No	List of monitor IDs linked to the maintenance window
`starts_at`	No	Date and time when the maintenance window starts, with minute precision (seconds must be `00`). Must be within the next year.
`created_at`	No	Date of creation for the entity
`project_id`	No	Parent project ID
`updated_at`	No	Date of last update for the entity
`description`	No	Description of the maintenance window
`status_pages`	No	List of status page IDs linked to the maintenance window
`monitoring_mode`	No	Monitoring mode during maintenance

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "created_at": {
+      "description": "Date of creation for the entity",
+      "format": "date-time",
+      "type": "string"
+    },
+    "description": {
+      "description": "Description of the maintenance window",
+      "examples": [
+        "Planned database upgrade and maintenance"
+      ],
+      "type": [
+        "string",
+        "null"
+      ]
+    },
+    "ends_at": {
+      "description": "Date and time when the maintenance window ends, with minute precision (seconds must be `00`). Must be after `starts_at` and within the next year.",
+      "format": "date-time",
+      "type": "string"
+    },
+    "id": {
+      "description": "Maintenance window ID",
+      "examples": [
+        1
+      ],
+      "type": "integer"
+    },
+    "monitoring_mode": {
+      "description": "Monitoring mode during maintenance",
+      "enum": [
+        "pause",
+        "mute",
+        "normal"
+      ],
+      "type": "string"
+    },
+    "monitors": {
+      "description": "List of monitor IDs linked to the maintenance window",
+      "examples": [
+        [
+          1,
+          2,
+          3
+        ]
+      ],
+      "items": {
+        "type": "integer"
+      },
+      "type": "array"
+    },
+    "project_id": {
+      "description": "Parent project ID",
+      "examples": [
+        1
+      ],
+      "type": "integer"
+    },
+    "starts_at": {
+      "description": "Date and time when the maintenance window starts, with minute precision (seconds must be `00`). Must be within the next year.",
+      "format": "date-time",
+      "type": "string"
+    },
+    "state": {
+      "description": "Maintenance window state",
+      "enum": [
+        "scheduled",
+        "in_progress",
+        "completed",
+        "cancelled"
+      ],
+      "type": "string"
+    },
+    "status_pages": {
+      "description": "List of status page IDs linked to the maintenance window",
+      "examples": [
+        [
+          1,
+          2
+        ]
+      ],
+      "items": {
+        "type": "integer"
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "tags": {
+      "description": "Resource tags, made of lowercase letters, numbers, `.`, `_`, `:` and `-`. An organization can have up to 200 tags.",
+      "items": {
+        "examples": [
+          "environment:production"
+        ],
+        "type": "string"
+      },
+      "type": [
+        "array",
+        "null"
+      ]
+    },
+    "title": {
+      "description": "Maintenance window title",
+      "examples": [
+        "Database upgrade"
+      ],
+      "type": "string"
+    },
+    "updated_at": {
+      "description": "Date of last update for the entity",
+      "format": "date-time",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedNov 7, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations cover the safety profile (readOnly=false, destructive=false, idempotent=false, openWorld=true), and the description adds genuine behavior beyond them: the window appears immediately on linked status pages, terminates on its own at `ends_at`, and `pause`/`mute`/`normal` change what happens to monitors meanwhile. It stops short of disclosing whether monitors are affected immediately at creation or only at `starts_at`, and says nothing about later editability.

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 dense but well-ordered paragraph: what is created first, then lifetime, then mode effects. No filler sentences and every clause carries information an agent needs before calling.

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 nine-parameter mutation with an output schema, annotations, and full schema coverage, the description covers the essentials: purpose, self-expiring lifetime, status-page visibility, and mode semantics. Minor gaps remain around timing of monitor effects and the optional `status_pages`/`tags` linkage, but the structured fields carry those details.

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?

With 100% schema coverage the baseline is 3, but the description earns more by explaining the semantics of the `monitoring_mode` enum values (`pause` pauses, `mute` keeps checking without incident alerts, `normal` only announces) — meaning the schema's terse 'Monitoring mode during maintenance' does not convey. Other parameters such as `status_pages` and `tags` are left entirely to the schema.

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?

States a specific verb and resource ('Schedule a maintenance window for monitors of the project') plus the scope (monitors of the project, linked status pages). It is clearly a creation tool, distinguishing it implicitly from update/cancel/delete siblings, but it never names those siblings or contrasts itself with them directly.

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 description gives useful decision guidance for the `monitoring_mode` choice by explaining what each mode does to monitors during the window. However, it offers no guidance on when to create a new window versus using update_maintenance_window, nor any prerequisites (e.g. project must exist, monitors must be known), leaving usage context implied.

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

All Phare tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?