Skip to main content
Glama

Delete restore point

delete_restore_point
Destructive

DESTRUCTIVE. Delete a restore point and sweep its objects from the backup vault (the twin of ankra cluster stacks restore-points delete). Nothing restores from it again. A restore point still being created, one a run is using, one on hold, or one under retention (retain_until in the future) is refused - relay that refusal rather than retrying. Deleting the only complete restore point of a protected stack is refused with error_code last_complete_restore_point until confirm is the stack's own name, typed exactly: tell the person the stack is left with nothing to restore from and ask them to type its name before calling again. Requires backups.manage.

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": {
      "stack_name": "<stack_name>",
      "restore_point_id": "<restore_point_id>"
    },
    "name": "delete_restore_point"
  }
}

Input Schema

NameRequiredDescriptionDefault
confirmNoThe stack name, typed exactly by the person, confirming the delete of the stack's only complete restore point. Needed only after a last_complete_restore_point refusal.
cluster_idNoUUID of the cluster. Alternative to cluster_name.
stack_nameYesThe stack the restore point belongs to.
cluster_nameNoExact name of the cluster. Optional when a cluster is already selected in the conversation.
restore_point_idYesRestore point id (UUID) from list_restore_points.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / confirm
      Added value: +{
      +  "description": "The stack name, typed exactly by the person, confirming the delete of the stack's only complete restore point. Needed only after a last_complete_restore_point refusal.",
      +  "type": "string"
      +}
  2. First observed

TDQS

A4.8/5.0
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 goes well beyond them: it names what is destroyed (objects swept from the vault), states irreversibility in functional terms, enumerates the four refusal states, supplies the specific error_code and confirm handshake, and names the required permission (backups.manage). This is exactly the extra context the annotations cannot carry.

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 DESTRUCTIVE lead is front-loaded and each subsequent sentence carries operational weight. The only low-value element is the parenthetical CLI twin reference, which does not help an agent decide or call correctly, and the paragraph is dense enough to warrant a second read.

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 destructive, non-idempotent mutation with no output schema, the description covers destruction scope, refusal conditions, error codes, the confirmation protocol, and the required permission. Nothing an agent needs before invoking it 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 is 3, but the description adds real meaning about confirm — the trigger (last_complete_restore_point refusal), the exact content required (the stack's own name typed exactly), and the human-in-the-loop step preceding it. That workflow linkage is not obvious from the field description alone.

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 (delete) and resource (a restore point) plus the side effect of sweeping its objects from the backup vault. It is clearly distinguishable from siblings like get_restore_point, list_restore_points, create_stack_restore_point, and restore_restore_point_in_place, which this description implicitly counterposes with 'Nothing restores from it again.'

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 concrete when-not conditions (still being created, in use by a run, on hold, under retention) and an explicit instruction to relay the refusal rather than retry. It also documents the escalation path for the last_complete_restore_point case, telling the agent exactly what to say to the person before calling again.

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.