Skip to main content
Glama
Sign In

Ankra

by ai.ankra
OverviewDiscussionsAdmin

Adopt stack profile

adopt_stack_profile

Record a stack a cluster already runs as a deployment of a stack profile, without changing the cluster (the twin of ankra stack-profiles adopt), so the profile's fleet view and rollouts include it. The answer reports drift: only_on_cluster lists the members a rollout of the version would remove. Requires stacks.write on the cluster.

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": {
      "target_cluster_id": "<target_cluster_id>",
      "stack_name": "<stack_name>"
    },
    "name": "adopt_stack_profile"
  }
}

Input Schema

NameRequiredDescriptionDefault
versionNoThe version the stack corresponds to; defaults to the current version.
parametersNoInput values as {name, value}. A secret input takes a ${SECRET_SLOT:<id>} reference, never a literal secret.
profile_idNoThe stack profile id (UUID) from list_stack_profiles. Give this or profile_name.
stack_nameYesThe stack's name on that cluster.
profile_nameNoThe stack profile's exact name, instead of profile_id.
target_cluster_idYesThe id of the cluster running the stack.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.6/5.0
Behavior5/5

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

Goes well past the annotations: it discloses that the cluster itself is not modified, that the side effect lands on the profile's fleet view and future rollouts, that the response includes a drift field (only_on_cluster) predicting what a rollout would remove, and that stacks.write is required on the cluster. These are exactly the traits an agent needs before triggering a non-readOnly, non-idempotent call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Three sentences, each earning its place: purpose and non-mutation first, then the returned drift semantics, then the permission prerequisite. No repetition of schema or annotation content.

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?

With no output schema, the description usefully explains the shape of the answer (only_on_cluster) and the auth requirement for a 6-parameter mutation tool. The remaining gap is failure behavior — what happens on repeat adoption or conflicting cluster state — which is not covered anywhere.

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: 'members a rollout of the version would remove' clarifies what the version parameter governs, and 'on the cluster' ties stacks.write and stack_name to target_cluster_id. It does not address the profile_id/profile_name choice, which the schema already handles.

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 and resource ('Record a stack a cluster already runs as a deployment of a stack profile') and immediately disambiguates with 'without changing the cluster', which separates it from mutation siblings like instantiate_stack_profile or rollout_stack_profile_version. The CLI twin reference anchors the mental model further.

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?

The 'without changing the cluster' clause effectively tells the agent when this is the right tool versus actually rolling out or instantiating a profile. It does not explicitly name the alternative tools or state when adoption should be refused (e.g. stack already adopted), so guidance is clear but not exhaustive.

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

All Ankra toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources