Skip to main content
Glama

File ticket

file_ticket
Destructive

File a new ticket on the AI work board: a gap you found, a follow-up chore, an incident to investigate, or a request on behalf of the user. The ticket enters 'triage' and the dispatcher assigns it to the best matching agent. Give it a clear title, a body with the evidence, a kind, and a priority. Tickets cannot target an archived cluster - file board-level (no cluster_id) work instead if genuinely needed. An incident or insight on a cluster MUST name the condition it reports and the object it is on (condition, resource_kind, resource_namespace, resource_name): the board keys the ticket on the problem class and the root-cause object, so the same fault already seen by an alert or an insight lands on their ticket as a recurrence instead of a duplicate, and the result tells you which happened. Name them for scan and audit findings of any kind too.

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>",
      "body": "<body>"
    },
    "name": "file_ticket"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesThe problem statement with evidence (markdown).
kindNoThe ticket kind (default 'request').
titleYesShort imperative title (e.g. 'Pin unversioned nginx addon on prod-eu').
priorityNoThe priority (default 'medium').
conditionNoThe unhealthy state this ticket reports, as a short stable name. Prefer a problem class: 'crashloop', 'oom', 'image_pull', 'config_error', 'unschedulable', 'pod_not_ready', 'workload_unavailable', 'job_failed', 'node_not_ready', 'node_pressure', 'node_unschedulable', 'storage_pending', 'storage_full', 'addon_unhealthy', 'certificate_not_ready', 'cluster_unreachable'; common spellings ('restart_accumulation', 'CrashLoopBackOff', 'ImagePullBackOff') map onto them, and an unknown name keys on itself. Requires a cluster; required for kind 'incident' and 'insight'. With resource_kind/resource_name it keys on that object's root cause (a pod resolves to its Deployment, DaemonSet or CronJob), otherwise on the cluster. Same class, same object, open ticket = recurrence, not a new ticket.
cluster_idNoThe cluster this concerns. Defaults to the session's cluster when scoped.
resource_kindNoThe Kubernetes kind of the object the condition is on (e.g. 'Pod', 'Deployment', 'Node', 'PersistentVolumeClaim'). Pass the pod when that is what you observed; the board resolves its owner workload. Goes with resource_name.
resource_nameNoThe name of that object. Goes with resource_kind.
resource_namespaceNoThe namespace of that object; omit for cluster-scoped kinds (Node, PersistentVolume). Used with condition.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior5/5

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

Beyond the annotations (readOnlyHint=false, destructiveHint=true, idempotentHint=false), the description discloses non-obvious outcomes: the ticket enters 'triage', a dispatcher assigns it to the best matching agent, and the board keys on problem class plus root-cause object so the same fault lands as a recurrence instead of a duplicate. It even notes the result reports which case occurred, which is exactly the context an agent needs given idempotentHint=false.

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?

Purpose and constraints are front-loaded in the first two sentences, with the keying rules following. The final clause ('Name them for scan and audit findings of any kind too') is loosely attached and the long condition sentence is dense, but nearly every sentence carries operational information.

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 9-parameter tool with no output schema, the description covers the workflow (triage/assignment), the archived-cluster restriction, and the full keying semantics for incident/insight tickets. Minor gaps remain: it never addresses the destructiveHint=true annotation, and return values are only hinted at via 'the result tells you which happened'.

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 already 100%, yet the description adds real meaning: condition names key the dedupe, resource_kind/resource_name pair up and a pod resolves to its owning Deployment/DaemonSet/CronJob, and namespace is used with condition. It clarifies cross-parameter interactions the schema only describes in isolation, lifting it above the baseline 3.

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 opens with a specific verb and resource ('File a new ticket on the AI work board') and enumerates what qualifies: gaps, chores, incidents, and user requests. The 'AI work board' scoping helps separate it from the support-ticket siblings in spirit, but no sibling is named explicitly, so an agent facing create_support_ticket must still infer which board to use.

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 states when to file (gap, chore, incident, request), a hard exclusion ('Tickets cannot target an archived cluster - file board-level (no cluster_id) work instead if genuinely needed'), and a MUST condition for incident/insight tickets that names the condition and object. Alternatives are only implied via the no-cluster_id fallback rather than routed to a named tool.

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.