OpenUptime

create_incident

Opens a manual incident in a project for events not already covered by automatic incidents, returning its record and UUID and optionally attaching an initial investigating update.

Instructions

Open a manual incident in the selected project and return its record and UUID. Use this for an event not already represented by an automatic incident; use post_incident_update for an existing incident. A monitorId limits it to pages containing that monitor; otherwise it applies to project status pages. The optional body becomes the first investigating update, public unless visibility is internal. Creation assigns the caller; it does not send subscriber update emails.

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": {
      "title": "<title>"
    },
    "name": "create_incident"
  }
}

Input Schema

Name	Required	Description	Default
`body`	No	Text of the initial investigating update; omit to create the incident without an initial update.
`title`	Yes	Short incident summary shown to the team and on relevant public status pages.
`project`	No	Project id (from list_workspaces). Omit to use the default project of the workspace.
`severity`	No	Incident impact level; major denotes a major outage and minor a smaller disruption.	major
`monitorId`	No	Monitor UUID from list_monitors; omit for a project-wide incident.
`workspace`	No	Workspace id (from list_workspaces). Omit to use the default one.
`visibility`	No	public publishes the update to status pages; internal keeps its text visible only to the team. Defaults to public.

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedv0.1.1Oct 23, 2026

addedInput schema / properties / body / description

Added value: +"Text of the initial investigating update; omit to create the incident without an initial update."

addedInput schema / properties / monitorId / description

Added value: +"Monitor UUID from list_monitors; omit for a project-wide incident."

addedInput schema / properties / severity / description

Added value: +"Incident impact level; major denotes a major outage and minor a smaller disruption."

addedInput schema / properties / title / description

Added value: +"Short incident summary shown to the team and on relevant public status pages."

addedInput schema / properties / visibility / description

Added value: +"public publishes the update to status pages; internal keeps its text visible only to the team. Defaults to public."

First observedv0.1.0Oct 19, 2026

TDQS

A4.5/5.0

Behavior4/5

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

Goes well beyond the annotations (readOnly=false, destructive=false, idempotent=false): it discloses that creation assigns the caller as owner, that the optional body becomes the first investigating update, that no subscriber update emails are sent, and that monitorId limits scope to pages containing that monitor. Missing only minor traits such as reversibility or permission/error behavior.

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 purpose and return value, then alternative routing, then scoping and side effects — every sentence carries information and there is no filler. Slight redundancy with the schema on the visibility default keeps it from a 5.

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 7-parameter, non-idempotent mutation with no output schema, the description supplies what the structured fields do not: the returned record/UUID, caller attribution, initial-update behavior, and the no-email side effect. Preconditions such as required permissions or invalid project IDs are left unstated.

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 baseline already covers all seven parameters; the description nevertheless adds semantic value by explaining what monitorId scoping actually means for incident visibility and that the body becomes the first investigating update. The visibility default is restated rather than extended, which keeps it below a 5.

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?

Opens with a specific verb and resource ("Open a manual incident in the selected project") and states the return value (its record and UUID). It explicitly distinguishes manual incidents from automatic ones and names post_incident_update as the sibling for existing incidents, so an agent can route correctly without reading sibling schemas.

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 an explicit when-to-use condition ("an event not already represented by an automatic incident") and an explicit alternative with its own condition ("use post_incident_update for an existing incident"). The monitorId sentence further narrows applicability by explaining the scoping effect of the parameter on which pages the incident appears.

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