Skip to main content
Glama

start_resource_maintenance

Idempotent

Put a VMware Aria resource into maintenance to stop alerts and data collection before planned work, with an optional timed window; preview changes until confirmed.

Instructions

[WRITE] Put one resource in maintenance so Aria stops alerting on it and collecting its data — use before planned work such as powering a VM or host off.

Pass duration_minutes OR end_time_ms for a timed window (state MAINTAINED; the resource returns to its prior state when it expires). Pass neither for manual maintenance (MAINTAINED_MANUAL) that lasts until end_resource_maintenance — easy to forget, so prefer a window.

Without confirm=True this only previews: it reads the resource and returns blast_radius (resource name and kind, each adapter's state, whether it is in maintenance now, and the requested window) and changes nothing. Show that to the user and get their explicit decision. Do not set confirm=True on your own because the user asked earlier: they have not seen what it changes yet. Refused with confirm=True: a resource already in maintenance (starting again would replace that window) and a resource whose state cannot be read.

Acting returns the state before and after, confirmed (true / false / null when the after-state could not be read — null is unknown, not failure) and a note. Undo: end_resource_maintenance, recorded only when the resource was known not to be in maintenance before.

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": {
      "resource_id": "<resource_id>"
    },
    "name": "start_resource_maintenance"
  }
}

Input Schema

NameRequiredDescriptionDefault
targetNoAria target name from config; default when omitted.
confirmNoFalse (default) returns the blast radius and changes nothing. True applies it.
end_time_msNoWindow end as epoch MILLISECONDS in the future. Not with duration_minutes.
resource_idYesResource UUID from list_resources (not the resource name).
duration_minutesNoWindow length in whole minutes, 1-525600. Not with end_time_ms.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv2.4.2
    • removedInput schema / properties / confirmed
      Removed value: -{
      -  "anyOf": [
      -    {
      -      "type": "boolean"
      -    },
      -    {
      -      "type": "null"
      -    }
      -  ],
      -  "default": null,
      -  "description": "Deprecated alias for confirm; removed in the next minor release. confirmed=False holds even when confirm=True.",
      -  "title": "Confirmed"
      -}
  2. Changed5 schema fields changedv1.16.0
    • addedInput schema / properties / confirm
      Added value: +{
      +  "default": false,
      +  "description": "False (default) returns the blast radius and changes nothing. True applies it.",
      +  "title": "Confirm",
      +  "type": "boolean"
      +}
    • addedInput schema / properties / confirmed / anyOf
      Added value: +[
      +  {
      +    "type": "boolean"
      +  },
      +  {
      +    "type": "null"
      +  }
      +]
    • changedInput schema / properties / confirmed / default
      Previous value: -falseNew value: +null
    • changedInput schema / properties / confirmed / description
      Previous value: -"Must be True to actually start maintenance. Default False = preview only."New value: +"Deprecated alias for confirm; removed in the next minor release. confirmed=False holds even when confirm=True."
    • removedInput schema / properties / confirmed / type
      Removed value: -"boolean"
  3. Addedv1.15.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations only cover the safety profile (write, non-destructive, idempotent); the description adds the whole operational contract: preview-vs-apply behavior, the two refusal cases (already maintained, unreadable state), exactly what blast_radius contains, the meaning of the returned `confirmed` tri-state including that null is unknown not failure, and the condition under which an undo record exists. The idempotentHint is consistent — a repeat call is refused rather than silently replacing a window.

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?

Front-loaded with the action and its effect, then modes, then the confirm workflow, then return values and undo — a logical order with no filler. It is on the long side and repeats the schema's exclusivity rule, but each paragraph carries decision-relevant information.

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

Completeness5/5

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

For a mutation tool with no output schema, it fully compensates: it describes the preview payload, the post-apply return shape, null semantics, refusal conditions, and the reversibility path. An agent has everything needed to call it safely without further exploration.

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%, and the schema already documents mutual exclusivity of duration_minutes/end_time_ms and the confirm default. The description still adds meaningful semantics the schema does not: the resulting states (MAINTAINED vs MAINTAINED_MANUAL), what happens at expiry, and the practical recommendation to pass a duration rather than neither.

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?

States a specific verb and resource ('Put one resource in maintenance') plus the concrete effect ('Aria stops alerting on it and collecting its data'), which is far more than the name alone conveys. It is also clearly distinguished from the sibling end_resource_maintenance, which is named as the undo path.

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?

Explicit about when to use it ('before planned work such as powering a VM or host off'), which mode to prefer ('prefer a window' over manual because manual is 'easy to forget'), and what to do instead (end_resource_maintenance to undo). The confirm=True protocol — preview first, show blast_radius, get explicit user decision, never self-confirm — is spelled out with the reasoning.

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