Skip to main content
Glama

pve_ceph_pool_create

Create a Ceph pool on a Proxmox node with customizable replication, placement groups, and CRUSH rules. Supports dry-run planning and erasure coding.

Instructions

MUTATION: create a Ceph pool.

RISK_MEDIUM: consumes cluster capacity per its size/pg_num settings. No upstream cmd-safety check exists for pool creation (cmd-safety's service enum is {osd, mon, mds} — covers neither pool nor filesystem). CAPTURE-or-declare: reads the current pool list before planning (also readable directly via pve_ceph_pool_list, ADVERSARIAL — taint marked when tracking is on); if unreadable -> complete=False. Dry-run by default (returns a PLAN); confirm=True executes (POST /nodes/{node}/ceph/pool) and returns {"status": "submitted", "result": }. No rollback primitive on this plane — revert with pve_ceph_pool_destroy(name=...).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesName of the new pool. Must be unique; no ':', '/', or whitespace.
nodeNoPVE node to create the pool on; defaults to the configured node if omitted.
sizeNoNumber of replicas per object (1-7, default 3).
pg_numNoNumber of placement groups (1-32768, default 128).
confirmNoFalse (default) returns a dry-run PLAN only; True executes the create.
min_sizeNoMinimum number of replicas per object to allow I/O (1-7, default 2).
crush_ruleNoCRUSH rule NAME to use for object placement (a string — NOT the numeric id pve_ceph_pool_list returns for this same field; pve_ceph_pool_status's crush_rule is ALREADY the same string type, no divergence there).
pg_num_minNoMinimum placement-group count the autoscaler may choose (<=32768, no declared lower bound).
applicationNoPool application: 'rbd' (default), 'cephfs', or 'rgw'.
target_sizeNoEstimated target size for the PG autoscaler: a number optionally suffixed with K/M/G/T (e.g. '10G').
add_storagesNoRegister a PVE storage entry using the new pool. Schema-defaults False for replicated pools, True for erasure-coded pools; omit to let PVE apply that default.
erasure_codingNoCreate an erasure-coded pool instead of replicated: a PVE propertyString 'k=<int>,m=<int>[,device-class=<class>][,failure-domain=<domain>][,profile=<profile>]' (k>=2 data chunks, m>=1 coding chunks required). Also creates an accompanying replicated metadata pool.
proximo_targetNoWhich configured Proxmox target to run this call against — a target name from your multi-target config (a specific PVE/PBS/PMG/PDM box). Omit to use the single/default target from the environment; the selection applies only to this call.
pg_autoscale_modeNoPG autoscaler mode: 'on', 'off', or 'warn' (default).
target_size_ratioNoEstimated target ratio of total pool capacity, for the PG autoscaler.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

With no annotations provided, the description fully shoulders the burden of behavioral disclosure. It details risk (RISK_MEDIUM, consumes capacity), dry-run/confirm mechanism, return values (PLAN or {status, result}), prerequisite reading of pool list with adversarial taint tracking, and the absence of rollback. This is comprehensive and goes beyond minimal requirements.

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?

The description is a dense block of text but is front-loaded with the core purpose. Every sentence delivers essential information without fluff. However, it could benefit from better structuring (e.g., bullet points or sections) to improve readability, which prevents a perfect score.

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?

Given the complexity (15 parameters, no annotations, output schema present), the description covers the main workflow: dry-run vs confirm, return types, prerequisite reading, and revert method. It does not elaborate on error handling or all edge cases, but it provides sufficient context for an AI agent to use the tool correctly.

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?

Although schema coverage is 100% (baseline 3), the description adds extra meaning for some parameters: it clarifies that crush_rule is a string name (not numeric id from pve_ceph_pool_list), explains erasure_coding format with an example, and notes default behavior for add_storages. This adds value beyond the schema, justifying a 4.

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?

The description explicitly states 'MUTATION: create a Ceph pool', clearly specifying the verb (create) and resource (Ceph pool). It distinguishes itself from sibling tools like pve_ceph_pool_destroy (revert), pve_ceph_pool_list (read), and pve_ceph_pool_set (update), leaving no ambiguity about its unique purpose.

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?

The description provides explicit guidance on when to use: it recommends reading the current pool list first (via pve_ceph_pool_list) and suggests setting complete=False if unreadable. It explains dry-run by default and confirm=True for execution. It also mentions the lack of a rollback primitive and points to pve_ceph_pool_destroy as a revert option, covering when-not-to-use and alternatives.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/john-broadway/proximo'

If you have feedback or need assistance with the MCP directory API, please join our Discord server