Skip to main content
Glama

Prepare service setup

prepare_service_setup
Destructive

Prepare the review of a new managed service (step one of ankra services setup). It records a review and returns its plan - the package, the cluster, the consumers, the parameters and whether the cluster has room for it - with the digest confirm_service_setup needs. Nothing is deployed. The region and data boundary default to the cluster's policy (get_service_cluster_policy), or unspecified when it has not declared one; parameters default to the package's. Show the plan to the user before confirming. Requires applications.deploy.

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": {
      "package_version_id": "<package_version_id>",
      "name": "<name>",
      "cluster_id": "<cluster_id>",
      "consumer_ids": "<consumer_ids>"
    },
    "name": "prepare_service_setup"
  }
}

Input Schema

NameRequiredDescriptionDefault
modeNocustomer runs the service on the cluster (the default); existing adopts one already there.
nameYesThe service's name, which also becomes its namespace: lower-case letters, digits and single hyphens, starting with a letter, at most 36 characters, and not a system namespace.
regionNoPhysical region. Defaults to the cluster's policy.
cluster_idYesCluster id (UUID) the service runs on.
parametersNoPackage parameters by name, as whole numbers (for example storage_gib, instances). Omitted ones take the package's defaults.
consumer_idsYesConsumer binding ids (UUIDs) the service is for, from bind_service_consumer or list_service_consumers.
data_boundaryNoData boundary. Defaults to the cluster's policy.
secret_referencesNoPackage secret inputs by name, each a credential grant id (UUID). Secret values are never accepted.
package_version_idYesPackage version id (UUID) from list_service_packages.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior4/5

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

Adds substantial context beyond the annotations: it creates a persisted review record, deploys nothing, returns a plan with package/cluster/consumers/parameters/capacity, and requires applications.deploy. There is mild tension with destructiveHint=true, which the description never reconciles — the annotation implies destructive mutation while the text emphasizes that nothing is deployed, so an agent may be unsure how much caution is warranted.

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?

Purpose is front-loaded in the first clause, followed by return shape, defaults, and safety instruction in a logical order. The middle sentence is heavily parenthetical and dense, but every clause carries information an agent needs.

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 covers the return value (plan contents plus digest), the non-deployment guarantee, permission requirement, and defaulting rules — enough for correct invocation. It does not mention that repeated calls create additional reviews (non-idempotent), though idempotentHint=false partially covers this.

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: region and data_boundary default to the cluster's policy (or `unspecified`), and parameters default to the package's when omitted. This defaulting behavior and its source tool are not derivable from the schema 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+resource with explicit scope: 'step one of `ankra services setup`', records a review and returns a plan, and names the downstream sibling confirm_service_setup with the digest it needs. An agent can distinguish it from prepare_service_disconnection/retirement and from confirm_service_setup without opening a 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?

Gives explicit when-to-use framing (step one), the follow-up action (pass the digest to confirm_service_setup), a required human-in-the-loop step ('Show the plan to the user before confirming'), and points to get_service_cluster_policy for defaulting semantics. Clear sequencing and no ambiguity about ordering.

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.