Skip to main content
Glama

Create stack restore point

create_stack_restore_point
Destructive

Take a restore point of a stack now (the twin of ankra cluster stacks restore-points create, and what 'back up shop now' means). It opens a backup run; watch it with get_data_run. The result carries not_carried - what the capture will not take - so report that rather than implying everything was copied. On a CloudNativePG stack whose Clusters do not carry the barman-cloud archiver its backup policy adds yet, it adds it first, which restarts the database instances one at a time (a brief primary failover); say so before confirming. Requires backups.operate.

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>"
    },
    "name": "create_stack_restore_point"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoShort note recorded with the restore point, e.g. why it was taken.
vault_idNoBackup vault id or name to write to. Omit to use the stack's protected vault, or the organisation's only ready one.
databasesNoWhether the stack's databases are captured. Setting it to false means the restore points carry no database contents at all. Naming it at all makes the selection explicit, so pair it with persistent_volume_claims unless you mean to capture the databases alone.
cluster_idNoUUID of the cluster. Alternative to cluster_name.
stack_nameYesThe stack to capture.
cluster_nameNoExact name of the cluster. Optional when a cluster is already selected in the conversation.
persistent_volume_claimsNoNames of the persistent volume claims to capture, from list_stack_data_assets. A selection is applied WHOLE, not merged with the stack's stored one: naming none of them captures no volumes at all. Send no selection (no databases, no persistent_volume_claims) to keep the stack's stored policy.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already flag destructiveHint=true and non-idempotent, but the description adds far more: the call is asynchronous and must be watched, the result carries a not_carried field the agent must surface rather than overclaim success, and on CloudNativePG stacks it may first add a barman-cloud archiver which restarts database instances and causes a brief primary failover. The required permission is stated explicitly.

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 action is front-loaded and every sentence carries operational weight — run tracking, the not_carried caveat, the archiver/failover warning, and the permission requirement. It is dense and slightly rambling in places, but nothing is redundant.

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 seven-parameter mutation with no output schema, the description covers the essential unknowns: it is asynchronous, how to observe it, what the result does not guarantee, a side effect that can restart databases, and the scope it requires. An agent could call it and warn the user correctly from this text alone.

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

Parameters3/5

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

Schema description coverage is 100%, so the parameters (including the whole-selection semantics of databases/persistent_volume_claims and the vault defaulting rule) are already well documented in the schema. The description itself adds no parameter-level detail beyond what the schema provides, so the baseline 3 applies.

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 names a specific verb and resource ('Take a restore point of a stack now') and anchors it against the CLI twin and the colloquial intent it maps to. It also clarifies the boundary against get_data_run by explaining that this call opens the run while that tool watches it.

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?

It gives clear when-to-use context (back up shop now, watch with get_data_run, report not_carried) and a precondition ('Requires backups.operate'). It also prescribes telling the user about a possible primary failover 'before confirming', which is real operational guidance, but it stops short of naming when a sibling such as restore_restore_point_in_place would be the right choice instead.

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.