Skip to main content
Glama

Create storage class

create_storage_class
Destructive

Create a new StorageClass on the cluster. Typed on purpose: the AI assistant may not write a StorageClass through patch_resource or delete_resource, and apply_manifest accepts one only under the same check. provisioner must be a CSI driver installed on the cluster (a CSIDriver of that name, or the provisioner an existing class already uses); the call is refused for an uninstalled provisioner, listing the installed ones. The name must be new: an existing class is never edited or replaced (Kubernetes does not let a class's provisioner, parameters or reclaim policy change in place). The new class is never made the cluster default and this tool cannot move the default. Before the confirmation card the cluster's StorageClasses, CSI drivers, volumes and claims are read live; if they cannot be read the call is refused with a 'Not checked' line, never passed. reclaim_policy Delete (the default) deletes a claim's volume and data with the claim; Retain keeps the volume until someone deletes it. Changing the default class, editing an existing class, or deleting a volume a claim uses stays with a person: the Ankra UI, ankra cluster apply (a manifest in the cluster's stack YAML), ankra cluster patch storageclass ... or ankra cluster delete ..., none of which the AI policy limits. Requires kubernetes.write.

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": {
      "name": "<name>",
      "provisioner": "<provisioner>",
      "cluster_id": "<cluster_id>"
    },
    "name": "create_storage_class"
  }
}

Input Schema

NameRequiredDescriptionDefault
nameYesName of the new StorageClass, a Kubernetes name (lowercase letters, digits, '-' and '.'). Must not exist yet.
cluster_idYesAnkra cluster id (UUID) the call targets. Discover ids with list_clusters.
parametersNoDriver-specific parameters, string keys to string values (e.g. {"type": "ssd", "fsType": "ext4"}). Numbers are written as strings.
provisionerYesThe CSI driver that provisions the class's volumes, exactly as the cluster names it (e.g. csi.hetzner.cloud, driver.longhorn.io, rancher.io/local-path).
reclaim_policyNoWhat happens to a volume when its claim is deleted. Defaults to Delete.
volume_binding_modeNoWhen a volume is provisioned: at claim time (Immediate, the default) or when the first pod using the claim is scheduled (WaitForFirstConsumer, preferred for zonal disks).
allow_volume_expansionNoWhether claims of this class may be resized larger later. Only set it when the CSI driver supports expansion.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and idempotentHint=false, but the description adds substantive behavior beyond them: pre-flight live reads of StorageClasses, CSI drivers, volumes and claims, a refusal with a 'Not checked' line if those reads fail, the guarantee that the new class is never made default, and the requirement for kubernetes.write. It also explains what is actually destroyed under reclaim_policy Delete (the claim's volume and data).

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 purpose and the sibling boundary are front-loaded in the first two sentences, and the remaining sentences carry distinct constraints rather than restating the name. It is dense and long, with the policy/alternatives sentence doing a lot of work, but virtually every clause adds a fact an agent needs.

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 7-parameter, non-idempotent, destructive mutation with no output schema, the description covers purpose, validation failures, pre-check behavior, permission scope, default-class immutability and the human-only escape hatches. Nothing an agent needs in order to call this correctly or to recognize a refusal reason is missing.

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%, so the baseline would be 3, but the description adds real meaning on top: provisioner must correspond to an installed CSIDriver or a provisioner an existing class already uses, the name must be new, and reclaim_policy Delete versus Retain is spelled out in terms of volume and data survival. volume_binding_mode and allow_volume_expansion are left to the schema, which keeps it just short of a 5.

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 opening sentence names a specific verb and resource ('Create a new StorageClass on the cluster') and immediately distinguishes it from siblings by declaring that patch_resource and delete_resource may not write a StorageClass and that apply_manifest only accepts one under the same check. An agent can route between create_storage_class, delete_storage_class, patch_resource and apply_manifest without opening any schema.

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?

Usage conditions and exclusions are both explicit: when the provisioner is not installed the call is refused and installed drivers are listed, when the name already exists the call cannot edit or replace, and changing the default, editing a class, or deleting a claim's volume is routed to a person via the Ankra UI, `ankra cluster apply`, `ankra cluster patch storageclass` or `ankra cluster delete`. That is a genuine when/when-not/alternative triad.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.