io.github.AIops-tools/ceph-aiops

osd_purge

Destructive

Permanently destroy a Ceph OSD, remove it from CRUSH, and delete its auth credentials. Preview with dry_run; drain and verify active+clean first.

Instructions

[WRITE][risk=high] Purge an OSD (destroy + crush rm + auth del). Irreversible.

Pass dry_run=True to preview. Drain first (osd_reweight 0 → mark out → wait active+clean) before purging.

Args: osd_id: Numeric OSD id (from osd_tree). dry_run: If True, preview without purging. target: Ceph target name from config; omit for the default.

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": {
      "osd_id": "<osd_id>"
    },
    "name": "osd_purge"
  }
}

Input Schema

Name	Required	Description	Default
`osd_id`	Yes
`target`	No
`dry_run`	No

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Jul 12, 2026

TDQS

A4.9/5.0

Behavior5/5

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

Annotations already declare destructiveHint=true and readOnlyHint=false, but the description adds material context: the operation is explicitly "Irreversible," it names the exact underlying steps (destroy + crush rm + auth del), and it documents the dry_run escape hatch. This exceeds the annotation bar with concrete destructive-behavior detail.

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?

Front-loaded with a [WRITE][risk=high] tag, then the core action, then the safety prerequisite, then a clean Args block. Every sentence earns its place with no redundancy.

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 high-risk destructive tool with no output schema, the description covers action, irreversibility, prerequisites, and parameter semantics well. The only minor gap is that it doesn't describe failure/partial-failure behavior across the three sub-operations (destroy/crush/auth), which would matter for a multi-step purge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must carry the burden — and it does: osd_id ("Numeric OSD id (from osd_tree)"), dry_run ("preview without purging"), and target ("Ceph target name from config; omit for the default"). All three parameters gain meaning absent from the bare schema.

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+resource ("Purge an OSD") and immediately unpacks what purging means ("destroy + crush rm + auth del"), which is far more specific than the tool name alone. It is easily distinguishable from the many read-only siblings (osd_tree, osd_df) and the milder mutation siblings (osd_mark_out, osd_reweight).

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 prerequisite sequence: "Drain first (osd_reweight 0 → mark out → wait active+clean) before purging," naming the sibling tools involved. It also points to the safe alternative ("Pass dry_run=True to preview"), so both when-to-use and how-to-de-risk are covered.

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