Skip to main content
Glama

Set service connection default

set_service_connection_default
Destructive

Choose which managed service gives one application environment a protocol's conventional connection names (DATABASE_URL and the PG* names for postgres, REDIS_URL for redis, NATS_URL, OPENSEARCH_URL, S3_ENDPOINT and AWS_* for s3, ...), or that none does. Every connected service is always delivered under its own prefix (ORDERS_DB_DATABASE_URL); the conventional names belong to one service per protocol, recorded the first time a deploy delivers them, and never move by themselves. When that service is retired while another service of the protocol still serves the environment, the application's deploys are refused until this is chosen (get_service_instance shows connection_delivery.holder_gone on the consumer). Name instance_id to choose a connected service, or none=true so the application reads only the prefixed names. Nothing is deployed: the next deploy delivers the choice. Requires applications.deploy and clusters.operate 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": {
      "application_id": "<application_id>",
      "cluster_id": "<cluster_id>",
      "namespace": "<namespace>",
      "protocol": "<protocol>"
    },
    "name": "set_service_connection_default"
  }
}

Input Schema

NameRequiredDescriptionDefault
noneNotrue to choose that no service provides the conventional names, so the application reads the prefixed names. Omit when instance_id is named.
protocolYesWire protocol whose conventional names are chosen.
namespaceYesNamespace of the application environment on that cluster.
cluster_idYesCluster id (UUID) the application environment runs on.
instance_idNoManaged service instance id (UUID) that provides the names; it must serve this environment over this protocol. Omit when none is true.
application_idYesApplication id (UUID).

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A4.3/5.0
Behavior4/5

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

Adds substantial behavior beyond the annotations: the effect is applied on the next deploy rather than immediately, it requires applications.deploy and clusters.operate on the cluster, conventional names are held by exactly one service per protocol and do not migrate on their own, and a missing choice blocks deploys. The one gap is that it never says the previous holder loses the conventional names when the default is moved, which is precisely what destructiveHint=true signals.

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 core action and the name mapping before the retirement edge case and the closing permission sentence; each sentence carries content. The protocol-name parenthetical is long and the body is a single dense paragraph, which costs a little scanability.

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?

For a six-parameter, no-output-schema configuration tool with a subtle domain model, the description covers naming semantics, the holder-retirement edge case, the deferred-apply behavior, and permissions. The missing piece is the impact on the service that previously held the conventional names, which an agent about to reassign a default would want to know.

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 would be 3, but the description adds real meaning: instance_id must be a connected service that actually serves this environment over this protocol, none=true restricts the app to prefixed names, and the protocol value determines which concrete names get delivered. The mutual exclusion of instance_id and none is spelled out here even though the schema does not encode it.

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 object: choose which connected service supplies a protocol's conventional names (DATABASE_URL/PG*, REDIS_URL, NATS_URL, OPENSEARCH_URL, S3_ENDPOINT/AWS_*), or that none does. It also draws the line against the always-on prefixed delivery (ORDERS_DB_DATABASE_URL), so an agent can distinguish this from bind_service_consumer-style binding without opening the schema.

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 the mandatory trigger explicitly: once the holding service is retired while another of the same protocol still serves the environment, deploys are refused until this choice is made, and get_service_instance surfaces connection_delivery.holder_gone on the consumer. It also states the two usage modes (instance_id vs none=true) and that nothing is deployed. It stops short of naming sibling tools to use instead for related tasks, so it is not a full when/when-not/alternatives statement.

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.