Skip to main content
Glama
bestpractical

mcp-server-rt

Official

update_lifecycle

Destructive

Replace a stored Request Tracker lifecycle by sending the full definition; omitted keys are dropped, so fetch the current config, modify, and send the whole object back to update.

Instructions

Update a lifecycle's configuration. Pass the full lifecycle definition including initial, active, inactive status arrays, transitions, rights, actions, and defaults. This REPLACES the stored configuration — any key you omit is dropped, including keys inherited from a create_lifecycle clone. RT fills in a missing defaults.on_create from the first initial status, and falls back to ModifyTicket — DeleteTicket for deleted — where rights are missing, but it does that in memory as it loads the config: neither key reappears in get_lifecycle, so one absent there is a working default rather than damage to repair. Omitted actions, colors, status_metadata and transition_metadata are simply lost. Cloning "default" inherits a full set of metadata, so omitting those two keys here silently strips the descriptions from every status. Use get_lifecycle first to get the current config, then modify and send the whole thing back. The lifecycle is validated before saving; any warning fails the update with a 400.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesLifecycle name to update
activeNoActive statuses (work in progress)
colorsNoStatus colors as {"status_name": "#hex_color"}. Colors appear in the RT web UI next to status names.
rightsNoRights required for transitions as {"from -> to": "RightName"}
actionsNoUI action buttons for transitions, keyed by transition: {"new -> open": {"label": "Open It", "update": "Respond"}}. RT also accepts its native flat array alternating transition string and info object (["new -> open", {"label": "Open It"}]), which is what get_lifecycle returns for lifecycles cloned from default — send that form back unchanged if you are not editing it. An array of {from, to, label} objects is REJECTED with a 400. "label" is the button text; "update" is optional and opens that form when clicked ("Respond" or "Comment"). Wildcards are allowed, e.g. "* -> resolved". The keyed form is ordered by sorted transition string; the array form keeps the order given.
initialNoInitial statuses (tickets start here)
defaultsNoDefault statuses (e.g. {on_create: "new", approved: "open"})
inactiveNoInactive statuses (finished/closed)
transitionsNoAllowed transitions as {from_status: [to_statuses]}. Use "" key for statuses available at creation.
status_metadataNoPer-status documentation, keyed by status name: {"stalled": {"description": "Blocked, waiting on something external.", "notes": "Note what you are waiting on."}}. "description" is human-facing, "notes" is guidance for an AI agent working the ticket. Both are optional free text; no other fields are allowed.
transition_metadataNoPer-transition documentation, keyed like rights: {"open -> resolved": {"description": "The work is complete.", "notes": "Resolve when the work is verified."}}. Same two optional fields as status_metadata. Wildcards are allowed ("* -> rejected"), and unlike rights, matching entries merge field by field with the more specific key winning.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Addedv0.3.0

TDQS

A4.5/5.0
Behavior5/5

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

The annotation already marks destructiveHint, and the description goes much further: it states replacement semantics, key omission behavior, in-memory default filling, metadata stripping for clones of 'default', and 400 on validation warnings. There is no contradiction with destructiveHint.

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?

The description is dense but each sentence covers a consequential behavior or workflow step. It is front-loaded with the action and replacement warning, and later sentences add edge-case detail rather than filler. A little more structural separation would improve scannability, but there is no wasted content.

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, 11-parameter tool with no output schema, the description covers the main workflow, validation failure mode, key-dropping behavior, and special metadata/default cases. It does not state the return value or explicitly identify the required lifecycle-name parameter, but the schema covers parameters and the invocation path is clear from get_lifecycle.

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. The description adds meaningful parameter-level guidance: the full definition must include initial/active/inactive/transitions/rights/actions/defaults; omitted status_metadata and transition_metadata are lost; and actions can accept the native array form that get_lifecycle returns. This goes beyond the schema's property descriptions.

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?

Description uses a specific verb ('Update'), identifies the resource ('a lifecycle's configuration'), and immediately clarifies that it replaces the stored configuration. This clearly distinguishes it from create_lifecycle and update_lifecycle_maps by emphasizing full-definition replacement.

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?

Explicitly instructs the agent to call get_lifecycle first, modify the current config, and send the whole thing back, and warns that omitted keys are dropped. It does not discuss alternatives like update_lifecycle_maps or validate_lifecycle, but the workflow and the destructive-replacement precondition are clear.

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

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bestpractical/mcp-server-rt'

If you have feedback or need assistance with the MCP directory API, please join our Discord server