Skip to main content
Glama

Post an incident on a status page

create_status_page_incident

Open a new incident on a public status page with its first message to inform visitors about an outage and email confirmed subscribers; confirm wording before posting.

Instructions

Open a new incident on a status page with its first message, to tell the page's visitors about an outage. It is public and emails the page's confirmed subscribers: confirm the wording with the user before calling. Any status but RESOLVED emails every confirmed subscriber at once; RESOLVED records an already closed incident (a postmortem) and emails nobody. To add to an existing incident use post_status_page_update. Requires a key with the write scope. Returns the incident. Example: {"page_id": "", "title": "API errors", "body": "We are investigating elevated error rates."}

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyYesThe first message. The message subscribers read, 1 to 5000 characters.
titleYesThe incident's headline, 1 to 255 characters.
statusNoINVESTIGATING, IDENTIFIED, MONITORING or RESOLVED; RESOLVED closes the incident on the page. Default INVESTIGATING.
page_idYesThe status page's uuid from list_status_pages. An id that is not a status page of this organization is a 404.
component_idsNoThe affected components: uuids from get_status_page. An id that is not a component of this page is a 404.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYes
titleYes
statusYesKnown values: INVESTIGATING, IDENTIFIED, MONITORING, RESOLVED.
is_autoYes
updatesYes
started_atYes
notified_atYes
resolved_atYes
component_idsYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed6 schema fields changedv0.6.1
    • addedInput schema / properties / body / description
      Added value: +"The first message. The message subscribers read, 1 to 5000 characters."
    • addedInput schema / properties / component_ids / description
      Added value: +"The affected components: uuids from get_status_page. An id that is not a component of this page is a 404."
    • addedInput schema / properties / page_id / description
      Added value: +"The status page's uuid from list_status_pages. An id that is not a status page of this organization is a 404."
    • addedInput schema / properties / status / description
      Added value: +"INVESTIGATING, IDENTIFIED, MONITORING or RESOLVED; RESOLVED closes the incident on the page. Default INVESTIGATING."
    • addedInput schema / properties / title / description
      Added value: +"The incident's headline, 1 to 255 characters."
    • changedOutput schema / (root)
      Previous value: -nullNew value: +{
      +  "properties": {
      +    "component_ids": {
      +      "items": {
      +        "format": "uuid",
      +        "type": "string"
      +      },
      +      "type": "array"
      +    },
      +    "id": {
      +      "format": "uuid",
      +      "type": "string"
      +    },
      +    "is_auto": {
      +      "type": "boolean"
      +    },
      +    "notified_at": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "resolved_at": {
      +      "anyOf": [
      +        {
      +          "type": "string"
      +        },
      +        {
      +          "type": "null"
      +        }
      +      ]
      +    },
      +    "started_at": {
      +      "type": "string"
      +    },
      +    "status": {
      +      "description": "Known values: INVESTIGATING, IDENTIFIED, MONITORING, RESOLVED.",
      +      "type": "string"
      +    },
      +    "title": {
      +      "type": "string"
      +    },
      +    "updates": {
      +      "items": {
      +        "properties": {
      +          "body": {
      +            "type": "string"
      +          },
      +          "created_at": {
      +            "type": "string"
      +          },
      +          "created_by": {
      +            "anyOf": [
      +              {
      +                "format": "uuid",
      +                "type": "string"
      +              },
      +              {
      +                "type": "null"
      +              }
      +            ]
      +          },
      +          "id": {
      +            "format": "uuid",
      +            "type": "string"
      +          },
      +          "status": {
      +            "description": "Known values: INVESTIGATING, IDENTIFIED, MONITORING, RESOLVED.",
      +            "type": "string"
      +          }
      +        },
      +        "required": [
      +          "id",
      +          "status",
      +          "body",
      +          "created_by",
      +          "created_at"
      +        ],
      +        "type": "object"
      +      },
      +      "type": "array"
      +    }
      +  },
      +  "required": [
      +    "id",
      +    "title",
      +    "status",
      +    "is_auto",
      +    "started_at",
      +    "resolved_at",
      +    "notified_at",
      +    "component_ids",
      +    "updates"
      +  ],
      +  "type": "object"
      +}
  2. First observedv0.5.4

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations: discloses that the incident is public, that it emails confirmed subscribers, the exact divergence between RESOLVED (records a closed incident/postmortem, emails nobody) and any other status (emails everyone at once), and the required write-scope key. The annotations only say it is a non-idempotent, non-destructive write; the description supplies the real blast radius.

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?

Dense but front-loaded: purpose, then notification behavior, then the sibling escape hatch, then auth, then an example. Every sentence carries information, though the example is somewhat redundant given a 100%-covered schema.

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 public, notification-triggering mutation with an output schema already present, the description covers purpose, routing, side effects and auth. Nothing material an agent needs to invoke it safely is missing.

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, and the description earns an upgrade by explaining the subscriber-notification semantics of the status enum and by showing a concrete call example with page_id, title and body. Component_ids and the length limits are left to the schema, which already documents them.

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 resource ('Open a new incident on a status page with its first message') and explicitly distinguishes itself from the sibling post_status_page_update, which adds to an existing incident. An agent can route between these two without opening either 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 the when (tell visitors about an outage), the when-not (adding to an existing incident → post_status_page_update), and a procedural precondition ('confirm the wording with the user before calling'). No inference required.

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