Skip to main content
Glama

Delete cluster

delete_cluster
Destructive

PERMANENTLY delete (deprovision) an Ankra-provisioned self-managed cluster: terminates every VM and cloud resource and removes the cluster from the platform. Configuration, workloads, and data are all destroyed; this cannot be undone. As a guardrail you MUST pass confirm_name exactly equal to the cluster's name - any mismatch refuses the deletion. Always have the user type or explicitly confirm the exact cluster name first. The delete also deletes the cluster's persistent volumes (the cloud volumes its CSI driver provisioned) and the data on them, unless the cluster's retention_policy keeps them. When the cluster has such volumes, or Ankra cannot read its volume inventory, the delete is refused unless accept_volume_data_loss is true: the refusal names the volumes, so show them to the user, ask whether they accept that the volumes and their data are deleted with the cluster, and call delete_cluster again with accept_volume_data_loss true only after the user has explicitly agreed.

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": {
      "confirm_name": "<confirm_name>"
    },
    "name": "delete_cluster"
  }
}

Input Schema

NameRequiredDescriptionDefault
cluster_idNoUUID of the target cluster. Optional when a cluster is selected.
cluster_nameNoExact name of the target cluster. Optional when a cluster is selected.
confirm_nameYesThe exact name of the cluster being deleted, echoed back as the deletion guardrail.
accept_volume_data_lossNoThe user's explicit consent that the cluster's persistent volumes, and the data on them, are deleted with the cluster. On a cluster with such volumes, or whose volume inventory Ankra cannot read, the delete is refused without it and the refusal names the volumes. Set it to true ONLY after you have shown the user those volumes and the user has explicitly agreed to lose that data - never on your own judgement, never pre-emptively, and not because the user asked to delete the cluster. Defaults to false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, but the description goes well beyond them: exact destruction surface (VMs, cloud resources, workloads, data, CSI-provisioned volumes), irreversibility, the confirm_name guardrail and refusal-on-mismatch behavior, the retention_policy exception, and the refusal-then-confirm loop for volume data loss. This is precisely the pre-call behavioral context an agent needs for an irreversible operation.

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 permanent/destructive framing and organized from what-happens to guardrail to volume-loss flow. It is dense and long, with some repetition of the accept_volume_data_loss semantics already in the schema, but the length is defensible for an irreversible delete.

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?

No output schema exists, but the description covers outcome (cluster and resources gone), failure modes (name mismatch refusal, volume-inventory refusal), and the recovery path (re-call with consent). For a 4-parameter destructive tool this leaves nothing material an agent needs unstated.

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 is 3, but the description adds real workflow meaning: confirm_name must match the cluster's name exactly or deletion is refused, and accept_volume_data_loss must only be set after showing the user the volumes named in the refusal. That sequencing guidance is not in the schema, though the per-parameter schema text already covers much of the same ground.

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?

Opens with a specific verb and resource plus scope qualifiers: "PERMANENTLY delete (deprovision) an Ankra-provisioned self-managed cluster," and immediately enumerates what that entails (VM termination, resource removal, platform removal). It is clearly distinguishable from siblings such as delete_cluster_mesh, delete_persistent_volumes, stop_cluster, and destroy_playground because it describes destroying the cluster itself.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives strong when-to-use procedure: confirm the exact cluster name with the user first, then pass it as confirm_name, and re-call with accept_volume_data_loss only after the user explicitly agrees to volume loss. It does not explicitly name alternatives (e.g., stop_cluster for temporary shutdown or delete_persistent_volumes for volumes alone), so a full 5 is not warranted.

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.