Phare

Create an incident update

create_incident_update

Destructive

Publish an update of an incident on the status pages and trigger the uptime.incident_update.published alert rules. Its state raises the state of the incident, and the resolved state recovers an ongoing incident.

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": {
      "project_id": "<project_id>",
      "incident_id": "<incident_id>",
      "state": "<state>",
      "content": "<content>"
    },
    "name": "create_incident_update"
  }
}

Input Schema

Name	Required	Description
`state`	Yes	State of the incident update
`content`	Yes	Content of the incident update
`project_id`	Yes	ID of the project to act on, see whoami
`incident_id`	Yes	ID of the incident
`published_at`	No	Date of publication of the incident update, defaults to the current date on creation. Must be within the last year and no more than 10 minutes in the future.

Output Schema

Name	Required	Description
`id`	No	Incident update ID
`state`	No	State of the incident update
`content`	No	Content of the incident update
`creator`	No	Creator of the incident update
`created_at`	No	Date of creation for the entity
`updated_at`	No	Date of last update for the entity
`published_at`	No	Date of publication of the incident update, defaults to the current date on creation. Must be within the last year and no more than 10 minutes in the future.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedNov 7, 2026

changedOutput schema / (root)

Previous value: -nullNew value: +{
+  "properties": {
+    "content": {
+      "description": "Content of the incident update",
+      "examples": [
+        "We are investigating the issue."
+      ],
+      "type": "string"
+    },
+    "created_at": {
+      "description": "Date of creation for the entity",
+      "format": "date-time",
+      "type": "string"
+    },
+    "creator": {
+      "description": "Creator of the incident update",
+      "properties": {
+        "id": {
+          "description": "Creator ID",
+          "examples": [
+            1
+          ],
+          "type": "integer"
+        },
+        "label": {
+          "description": "Creator label",
+          "examples": [
+            "nicolas@phare.io"
+          ],
+          "type": "string"
+        },
+        "type": {
+          "description": "Creator type",
+          "enum": [
+            "user",
+            "api_key"
+          ],
+          "examples": [
+            "user"
+          ],
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "id": {
+      "description": "Incident update ID",
+      "examples": [
+        1
+      ],
+      "type": "integer"
+    },
+    "published_at": {
+      "description": "Date of publication of the incident update, defaults to the current date on creation. Must be within the last year and no more than 10 minutes in the future.",
+      "format": "date-time",
+      "type": "string"
+    },
+    "state": {
+      "description": "State of the incident update",
+      "enum": [
+        "unknown",
+        "investigating",
+        "identified",
+        "monitoring",
+        "resolved"
+      ],
+      "type": "string"
+    },
+    "updated_at": {
+      "description": "Date of last update for the entity",
+      "format": "date-time",
+      "type": "string"
+    }
+  },
+  "type": "object"
+}

First observedNov 7, 2026

TDQS

A3.8/5.0

Behavior4/5

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

The annotations already flag a non-idempotent, destructive, open-world write, and the description adds substantive context beyond them: updates are externally visible on status pages, alert rules fire as a side effect, and the state transition only ratchets upward except that `resolved` recovers the incident. It still omits permission requirements and whether re-publishing duplicates notifications.

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, both front-loaded with the highest-value facts (external publication, alert triggering) before the state semantics. No filler or redundant restatement of the title.

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 destructive, open-world mutation with an output schema and fully documented parameters, the description covers the important behavioral consequences: public visibility, alert fan-out, and state progression. Missing only edge-case guidance such as duplicate updates or required permissions.

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 coverage is 100%, so the baseline is 3 regardless. The description does add real meaning for the `state` parameter by explaining that it escalates the incident's state and that `resolved` closes it, but it says nothing about content or published_at backdating beyond the schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description gives a specific verb and resource ("Publish an update of an incident on the status pages") and adds the side effect of triggering alert rules, which is more than the name conveys. It does not explicitly distinguish itself from near-siblings like update_incident_update or recover_incident, so it stops short of a 5.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Usage is implied rather than stated: because publishing an update is how incident state advances and because the `resolved` state recovers an incident, an agent can infer this is the tool for status-page communication and resolution. However, there is no explicit guidance on when to prefer update_incident_update over this tool, or when recover_incident should be used instead.

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

All Phare tools Inspect

Try in Browser

Claude Code, inside the Godot 4 editorFlockbay puts an AI agent in the real Godot 4 editor: it writes GDScript, runs your game and fixes what breaks. Free, or bring your own Claude Code or Codex.flockbay.comAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources

Need Help?