Skip to main content
Glama

Courier

by io.github.trycourier
OverviewDiscussionsAdmin

replace_notification

Idempotent

Replace a notification template entirely (full document PUT). The template stays a draft; making it live is a separate step this tool cannot perform.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
stateNoMust be "DRAFT". These tools cannot publish.
notificationYesFull notification template payload
notification_idYesThe notification template ID to replace. Copy it exactly, character for character, from the response that returned it — never retype it from memory or reconstruct it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed17 schema fields changed
    • changedInput schema / properties / notification / properties / brand / anyOf
      Previous value: -[
-  {},
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "id": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "id"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / notification / properties / brand / description
      Added value: +"Brand to apply, or null for none. Required on every call — never omit this key, and never send {}."
    • addedInput schema / properties / notification / properties / content / additionalProperties
      Added value: +false
    • addedInput schema / properties / notification / properties / content / description
      Added value: +"Elemental content, required on every call. Example: { version: \"2022-01-01\", elements: [{ type: \"text\", content: \"Hello!\" }] }."
    • addedInput schema / properties / notification / properties / content / properties
      Added value: +{
+  "elements": {
+    "description": "Elemental content nodes",
+    "items": {
+      "additionalProperties": {},
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "version": {
+    "description": "Content version identifier, e.g. \"2022-01-01\"",
+    "type": "string"
+  }
+}
    • addedInput schema / properties / notification / properties / content / required
      Added value: +[
+  "version",
+  "elements"
+]
    • addedInput schema / properties / notification / properties / content / type
      Added value: +"object"
    • addedInput schema / properties / notification / properties / name / description
      Added value: +"Template display name"
    • changedInput schema / properties / notification / properties / routing / anyOf
      Previous value: -[
-  {},
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "strategy_id": {
+        "description": "From a get_routing_strategy or list_notifications/get_notification response for THIS template's own intended strategy — never an id borrowed from an unrelated template found while searching for one.",
+        "type": "string"
+      }
+    },
+    "required": [
+      "strategy_id"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / notification / properties / routing / description
      Added value: +"Routing strategy reference, or null to use the workspace default. Required on every call — never omit this key, and never send {}: the API rejects both an absent routing key and an empty object; if you have no strategy id, send null explicitly."
    • changedInput schema / properties / notification / properties / subscription / anyOf
      Previous value: -[
-  {},
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "topic_id": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "topic_id"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]
    • addedInput schema / properties / notification / properties / subscription / description
      Added value: +"Subscription topic reference, or null for none. Required on every call — never omit this key, and never send {}."
    • addedInput schema / properties / notification / properties / tags / description
      Added value: +"Tag list (use [] if none)"
    • changedInput schema / properties / notification / required
      Previous value: -[
-  "name",
-  "tags"
-]New value: +[
+  "name",
+  "tags",
+  "brand",
+  "subscription",
+  "routing",
+  "content"
+]
    • changedInput schema / properties / notification_id / description
      Previous value: -"The notification template ID to replace"New value: +"The notification template ID to replace. Copy it exactly, character for character, from the response that returned it — never retype it from memory or reconstruct it."
    • changedInput schema / properties / state / description
      Previous value: -"Template state after update (defaults to DRAFT)"New value: +"Must be \"DRAFT\". These tools cannot publish."
    • changedInput schema / properties / state / enum
      Previous value: -[
-  "DRAFT",
-  "PUBLISHED"
-]New value: +[
+  "DRAFT"
+]
  2. Added

TDQS

A4.4/5.0
Behavior5/5

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

Annotations only provide readOnly=false, idempotent=true, destructive=false. The description adds meaningful behavioral context: full-document PUT semantics, the template remains a draft after replacement, and publication is explicitly out of scope. This goes beyond the annotations and is consistent with them.

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?

Two sentences with no filler. The core action and full-document semantics are front-loaded, and the critical draft-state limitation is stated immediately in the second sentence.

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?

The description covers the non-obvious behavioral facts—full replacement, draft-only state, no publishing—while the schema handles payload requirements. It does not describe the response shape, but no output schema exists and the key calling constraints are well covered.

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%, and the schema itself contains detailed parameter guidance, including warnings about never omitting keys or sending empty objects. The tool description adds no parameter-level information, so the schema-heavy baseline of 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 states a specific action ('Replace') on a specific resource ('notification template') and clarifies it is a 'full document PUT'. This distinguishes it from partial-update tools like put_notification_content and from publish_notification via the draft-state note.

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 clearly communicates a key exclusion: making the template live is a separate step this tool cannot perform. It does not name sibling alternatives explicitly, but the draft-versus-live boundary gives agents enough context to avoid using this tool for publishing.

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

All Courier 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