Skip to main content
Glama

Check if stopping/destroying a Ceph daemon is safe

proxmox_check_ceph_safety
Read-only

Check Ceph cluster safety before stopping or destroying an OSD, monitor, or MDS; confirms no placement groups become unavailable. Run it before delete or stop actions.

Instructions

Ask Ceph whether stopping or destroying an OSD, monitor or MDS is safe right now (e.g. no PGs would become unavailable). Call before proxmox_delete_ceph_osd, proxmox_delete_ceph_service or stopping services.

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": {
      "service": "<service>",
      "id": "<id>",
      "action": "<action>"
    },
    "name": "proxmox_check_ceph_safety"
  }
}

Input Schema

NameRequiredDescriptionDefault
idYesDaemon ID, e.g. '3' for osd.3 or the monitor name
nodeNoNode to query through (any node with Ceph installed; default PROXMOX_DEFAULT_NODE or the first online node). Results are cluster-wide.
actionYesIntended action
serviceYesDaemon type

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.6.1

TDQS

A4.4/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered; the description adds the important nuance that this is a point-in-time ('right now') verdict tied to PG availability. It stops short of explaining what a negative verdict looks like or that the answer can go stale between check and action.

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?

Two sentences: what the tool answers, then when to call it. The safety question and the PG criterion are front-loaded with no filler, and the gating instruction follows immediately.

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?

No output schema exists, yet the description never indicates whether the response is a boolean, a verdict with reasons, or a list of would-be-affected PGs — a real gap for a gate an agent must branch on. Everything else an agent needs to call it correctly (daemon type, id, action, cluster-wide node semantics) is present.

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 service, id, action and node are all self-documenting; the description adds no syntax or format detail beyond them. The 'no PGs would become unavailable' phrasing only loosely reinforces the stop/destroy distinction already expressed by the action enum.

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 (check) plus the exact resource scope ('stopping or destroying an OSD, monitor or MDS') and the semantic criterion being checked ('no PGs would become unavailable'). That is enough for an agent to distinguish this read-only safety gate from the sibling get_/list_ Ceph tools that merely read state.

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?

Gives an explicit call-before sequence: invoke this before proxmox_delete_ceph_osd, proxmox_delete_ceph_service, or any service stop. That is a when-to-use rule plus the alternative behavior (destructive ops) it gates, which is exactly what an agent needs for routing.

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