Skip to main content
Glama

Create notification route

create_notification_route
Destructive

Create a notification route: deliver notifications matching the given kind/severity/cluster/source/application/reference filters to an existing alert destination. To send one application's default-branch CI failures to a channel: kind pipeline_run_failed, application_id, reference_pattern 'main' (or the repository's default branch). Defaults: priority 100, include mode, enabled, no stop-on-match. Pick an existing destination id with list_alert_destinations (create_alert_destination adds a Slack or Teams channel destination; webhook destinations are created in the portal or CLI because their URLs are credentials). Verify the result with preview_notification_routing.

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": {
      "destination_id": "<destination_id>"
    },
    "name": "create_notification_route"
  }
}

Input Schema

NameRequiredDescriptionDefault
kindNoSingle notification kind to match; alternative to kinds.
modeNoinclude delivers matches; exclude suppresses them.
kindsNoNotification kinds to match. With kinds_negated, every kind EXCEPT these.
enabledNoWhether the route is active (default true).
priorityNoEvaluation order, lower first (default 100).
severityNoOnly notifications of this severity (critical, warning, info); omit for all.
source_idNoOnly notifications from this source identifier. At delivery today a notification's source is the id of the alert that fired, so filter on an alert id. At most 512 bytes and 4 uuids. A source you may not read (another project's cluster, alert, repository and the like) answers Source not found, as preview_notification_routing does.
cluster_idNoOnly notifications from this cluster (UUID); omit for all clusters.
kinds_negatedNoInvert the kinds list: match every kind except the listed ones.
stop_on_matchNoStop evaluating lower-priority routes when this one matches.
application_idNoOnly notifications about this application (UUID from list_applications), e.g. one application's pipeline failures; omit for all applications.
destination_idYesAlert destination id (UUID) from list_alert_destinations.
reference_patternNoOnly notifications about a branch, tag or pull request matching this glob: 'main' or 'refs/heads/main' for the main branch (pull requests targeting main do NOT match), 'release/*' within one path segment, 'release/**' across segments, 'pull/*' for every pull request, 'refs/tags/v*' for tags. Omit for all references.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / source_id / description
      Previous value: -"Only notifications from this source identifier."New value: +"Only notifications from this source identifier. At delivery today a notification's source is the id of the alert that fired, so filter on an alert id. At most 512 bytes and 4 uuids. A source you may not read (another project's cluster, alert, repository and the like) answers Source not found, as preview_notification_routing does."
  2. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare this is non-read-only, non-idempotent, and destructive; the description adds useful behavioral context such as default priority, include mode, enabled state, and no stop-on-match. It does not fully spell out the destructive impact of suppressing or redirecting notifications, but it supplies enough beyond the annotations to call the tool correctly.

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?

The description is front-loaded, stays to three sentences, and every part contributes: purpose, workflow prerequisites, defaults, example, and verification. There is no unnecessary repetition or filler.

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 13-parameter creation tool with no output schema, the description covers the essential context: what it creates, prerequisites, defaults, a real example, and how to verify the result. The rich input schema handles parameter details, so no critical behavior is left unexplained.

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 schema already carries detailed parameter explanations. The description adds a concrete example using kind pipeline_run_failed, application_id, and reference_pattern 'main', which helps an agent understand how filters combine in practice.

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 states a specific verb and resource: create a notification route that delivers notifications matching filters to an existing alert destination. It clearly distinguishes this from destination creation and route inspection by naming the destination prerequisite and verification step.

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?

It gives concrete workflow guidance: pick an existing destination with list_alert_destinations, use create_alert_destination for Slack/Teams channels, use portal/CLI for webhook destinations, and verify with preview_notification_routing. The example of routing an application's default-branch CI failures makes the intended use case explicit.

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.