Skip to main content
Glama

Ticket update status

ticket_update_status
Destructive

Move an AI work board ticket through its lifecycle: triage -> investigating -> planning -> awaiting_review -> awaiting_approval -> executing -> verifying -> done, with blocked/cancelled side exits. Transitions are validated; an invalid move is rejected with the reason. Moving to 'done' requires an explicit resolution - there is no default: fixed, no_action, duplicate, wont_fix, escalated, unverifiable (applied but never confirmed against live state), cleared (the alert stopped firing after an action, with nothing checking the resource), expired (the board's own gate clock writes this when a human gate lapsed unanswered - do not close as expired yourself). 'fixed' means the condition was corrected AND that was confirmed, so it is refused unless you also pass evidence_kind and evidence_reference naming what proves it. If you could not confirm the fix, do not close as fixed: use unverifiable, or move the ticket to 'blocked' and say what you could not verify. Always include a note explaining the move. Moving to 'executing' requires a human-approved plan, and 'awaiting_approval' requires a drafted plan - both are enforced. Desks that require agent review (and have a reviewer configured) also demand the peer verdict before 'awaiting_approval': request one with ticket_request_review first. When you move to 'blocked' because a human must choose between changes, pass them as decision_options (with a decision_prompt) so the board renders them as a choice - the human picks one or answers with something else, and their answer comes back in your next brief as a Human decision to act on. Never ask a human for permission to read: every read needs no approval, the break-glass ssh_kubectl_read included, so do the read yourself; an option declared read_only is refused. After a human answered, a move to 'blocked' is refused until the run has made a tool call other than the ticket tools.

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": {
      "status": "<status>"
    },
    "name": "ticket_update_status"
  }
}

Input Schema

NameRequiredDescriptionDefault
noteNoWhy the ticket is moving (posted on the timeline).
statusYesThe target lifecycle status.
ticket_idNoThe ticket UUID. Optional when ticket_number is given.
resolutionNoRequired when moving to done; there is no default.
duplicate_ofNoOnly with status 'done' and resolution 'duplicate': the number of the open ticket that covers the same cause. The board links the two, so whoever reads either ticket finds the other.
evidence_kindNoWhat confirmed the fix. Required with resolution 'fixed', and must be given together with evidence_reference.
ticket_numberNoThe per-organisation ticket number.
decision_promptNoOnly with status 'blocked': the one-sentence question the human must answer.
decision_optionsNoOnly with status 'blocked', when the block is a choice between changes: the options the human picks from on the board (they can also answer with something else in their own words). Their answer comes back in your next brief as a Human decision to act on. Every option must declare an action_class, 'mutating' or 'none': never offer a read as an option - do the read yourself, every read needs no approval.
evidence_referenceNoThe evidence itself: the probe or run id, the URL, or the tool you read and the exact values you saw. Required with resolution 'fixed'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed5 schema fields changed
    • changedInput schema / properties / decision_options / description
      Previous value: -"Only with status 'blocked', when the block is a choice between alternatives: the options the human picks from on the board (they can also answer with something else in their own words). Their answer comes back as a comment starting with 'Decision:'. Give every option an action_class: it is what lets the board settle the question safely if nobody answers before the organisation's deadline."New value: +"Only with status 'blocked', when the block is a choice between changes: the options the human picks from on the board (they can also answer with something else in their own words). Their answer comes back in your next brief as a Human decision to act on. Every option must declare an action_class, 'mutating' or 'none': never offer a read as an option - do the read yourself, every read needs no approval."
    • changedInput schema / properties / decision_options / items / properties / action_class / description
      Previous value: -"What taking this option would DO: 'none' changes nothing (do nothing, silence it, leave it), 'read_only' gathers more information without changing anything, 'mutating' changes a cluster or the platform. Declare it honestly. It is what lets a deadline settle an unanswered question safely: an option that declares nothing, or declares 'mutating', is never taken automatically."New value: +"What taking this option would DO: 'none' changes nothing (do nothing, silence it, leave it), 'mutating' changes a cluster or the platform. Required, and declared honestly: it is what lets a deadline settle an unanswered question safely, and a 'mutating' option is never taken automatically. 'read_only' is refused - a read is never a question for a human."
    • changedInput schema / properties / decision_options / items / properties / action_class / enum
      Previous value: -[
      -  "none",
      -  "read_only",
      -  "mutating"
      -]New value: +[
      +  "none",
      +  "mutating"
      +]
    • changedInput schema / properties / decision_options / items / required
      Previous value: -[
      -  "title"
      -]New value: +[
      +  "title",
      +  "action_class"
      +]
    • addedInput schema / properties / duplicate_of
      Added value: +{
      +  "description": "Only with status 'done' and resolution 'duplicate': the number of the open ticket that covers the same cause. The board links the two, so whoever reads either ticket finds the other.",
      +  "minimum": 1,
      +  "type": "integer"
      +}
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Beyond the annotations (destructive=true, non-idempotent) it discloses enforced preconditions: transitions are validated and rejections carry a reason; 'executing' requires a human-approved plan; 'awaiting_approval' requires a drafted plan plus peer verdict; 'fixed' is refused without evidence_kind plus evidence_reference; and a post-answer move to 'blocked' is refused until a non-ticket tool call is made. No contradiction with the destructive/non-idempotent annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loading is good — lifecycle map first, then rules — and every sentence carries a constraint. But it is one dense block that drifts between topics (evidence semantics, peer review, blocked decisions, read policy, post-answer gating), and the 'never ask a human for permission to read' rule is repeated inside the decision_options schema, so structure and economy are merely adequate.

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 10-parameter, destructive, gate-heavy tool with no output schema, the description covers the state machine, prerequisites, evidence rules, and the blocked-decision round trip. It does not say what the call returns (e.g., the updated ticket or rejection payload shape), which would matter given there is no output schema, but otherwise it is complete enough to call correctly.

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, but the description adds genuine semantics the schema lacks: the meaning of each resolution value (unverifiable = applied but never confirmed, cleared = alert stopped with nothing checking, expired = board gate clock only) and the cross-parameter coupling of fixed to evidence fields. It restates some schema text (the decision_options guidance largely duplicates the field description), which keeps it from 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 ('Move an AI work board ticket') and immediately enumerates the full lifecycle state machine including side exits, so the agent knows exactly what operation it is and what targets are legal. It is clearly distinguishable from siblings like ticket_comment or ticket_draft_plan.

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 explicit routing: use ticket_request_review first when a desk requires peer verdict; use 'unverifiable' or 'blocked' instead of 'fixed' when the fix is unconfirmed; never self-close as 'expired'; pass decision_options to blocked when a human must choose. It also states what is not permitted (declaring a read_only option, asking a human for read permission) and names the break-glass sibling ssh_kubectl_read.

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.