Skip to main content
Glama
SmartBear

SmartBear MCP server

Official
by SmartBear

QTM4J: Create Test Cycle

qtm4j_create_test_cycle

Create a test cycle in a QTM4J project with priority, status, labels, components, and planned dates. Automatically resolves names and uses the default folder for test planning.

Instructions

Create a new test cycle in a QTM4J project. Supports auto-resolving human-readable names for priority and status. projectId is injected automatically from the active project context.

Toolset: Test Cycles

Parameters:

  • summary (string) required: Short title of the test cycle. Must not be blank. Max 255 chars.

  • description (string): Detailed description of the test cycle. Max 65 535 characters.

  • priority (string): Priority name (e.g., 'High', 'Medium', 'Low'). Auto-resolved to ID.

  • status (string): Status name (e.g., 'To Do', 'In Progress', 'Done'). Auto-resolved to ID.

  • folderId (number): Numeric folder ID where the test cycle will be created. If omitted, the cycle is created in the 'MCP Generated' folder automatically.

  • assignee (string): Assignee account ID

  • reporter (string): Reporter account ID

  • labels (array): List of label names (e.g., ['Release_1', 'Sprint 1']). Auto-resolved to IDs.

  • components (array): List of component names (e.g., ['UI', 'Cloud']). Auto-resolved to IDs.

  • plannedStartDate (string): Planned start date. Format: 'dd/MMM/yyyy HH:mm' e.g. '10/May/2026 00:00'. Must be ≤ plannedEndDate when both are provided.

  • plannedEndDate (string): Planned end date. Format: 'dd/MMM/yyyy HH:mm' e.g. '15/May/2026 00:00'. Must be ≥ plannedStartDate when both are provided.

Output Description: JSON object with the new test cycle's id and key (e.g. 'TRWT-TR-218'). Warnings included if any fields were skipped.

Use Cases: 1. Create a test cycle with summary, priority, status, labels, or components 2. Set planned start and end dates on a new test cycle

Examples:

  1. Create a simple test cycle (project must be set via set_project_context first)

{
  "summary": "Smoke Test Cycle"
}

Expected Output: Test cycle created with key 'SCRUM-TR-xxx'

  1. Create a test cycle with priority, status, labels, and components

{
  "summary": "Regression Suite – Sprint 42",
  "description": "End-to-end regression covering payment and checkout modules.",
  "priority": "High",
  "status": "To Do",
  "labels": [
    "Release_1",
    "Sprint 1"
  ],
  "components": [
    "UI",
    "Cloud"
  ],
  "plannedStartDate": "10/May/2026 00:00",
  "plannedEndDate": "15/May/2026 00:00"
}

Expected Output: Test cycle created with resolved priority, status, labels, and components

Hints: 1. PREREQUISITE: set_project_context must be called before this tool. NEVER auto-select a project. 2. If any priority, status, label, or component name cannot be resolved, the cycle is still created but a warning is returned. Suggest the closest available value from the set_project_context response and ask the user to confirm before retrying. 3. FOLDER ID: folderId is optional. If omitted, defaults to the 'MCP Generated' folder. To place in a specific folder, ask the user to right-click the target folder in QTM4J and select 'Copy Folder Id' — never try to look it up. 4. Date format: 'dd/MMM/yyyy HH:mm' e.g. '10/May/2026 00:00'. Month must be capitalised. plannedStartDate must be ≤ plannedEndDate.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
labelsNoList of label names (e.g., ['Release_1', 'Sprint 1']). Auto-resolved to IDs.
statusNoStatus name (e.g., 'To Do', 'In Progress', 'Done'). Auto-resolved to ID.
summaryYesShort title of the test cycle. Must not be blank. Max 255 chars.
assigneeNoAssignee account ID
folderIdNoNumeric folder ID where the test cycle will be created. If omitted, the cycle is created in the 'MCP Generated' folder automatically.
priorityNoPriority name (e.g., 'High', 'Medium', 'Low'). Auto-resolved to ID.
reporterNoReporter account ID
componentsNoList of component names (e.g., ['UI', 'Cloud']). Auto-resolved to IDs.
descriptionNoDetailed description of the test cycle. Max 65 535 characters.
plannedEndDateNoPlanned end date. Format: 'dd/MMM/yyyy HH:mm' e.g. '15/May/2026 00:00'. Must be ≥ plannedStartDate when both are provided.
plannedStartDateNoPlanned start date. Format: 'dd/MMM/yyyy HH:mm' e.g. '10/May/2026 00:00'. Must be ≤ plannedEndDate when both are provided.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idYesOpaque permanent identifier of the created test cycle. Use this in all subsequent API calls.
keyYesHuman-readable project-scoped key in format '<PROJECT_KEY>-TR-<number>'. e.g. 'TRWT-TR-218'.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.41.3
    • addedInput schema / properties / folderId
      Added value: +{
      +  "description": "Numeric folder ID where the test cycle will be created. If omitted, the cycle is created in the 'MCP Generated' folder automatically.",
      +  "exclusiveMinimum": 0,
      +  "maximum": 9007199254740991,
      +  "type": "integer"
      +}
  2. Addedv0.40.0
  3. Removedv0.34.0
  4. First observedv0.27.1

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly=false, idempotent=false, destructive=false, and the description does not contradict them. Beyond annotations it discloses non-obvious behavior: name-to-ID auto-resolution for priority/status/labels/components, that the cycle is still created with a warning when resolution fails, the 'MCP Generated' folder default, and the date ordering constraint.

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, prerequisites, then parameters, use cases, examples, and hints – a logical order. It is long and the parameter list duplicates the JSON schema descriptions verbatim, which is redundant bulk, but the Hints and Examples sections carry real value.

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?

An output schema exists so return values need not be described, and the description nonetheless sketches the response ('id and key' plus warnings). Every decision an agent must make for an 11-parameter create tool – prerequisite, folder placement, date format, failure handling – is covered.

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 mostly restates those parameter descriptions verbatim. It earns above baseline by adding semantic context the schema lacks: how folderId resolves when omitted, how arbitrary names are auto-resolved to IDs, and the retry/confirm workflow when resolution fails.

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 ('Create a new test cycle in a QTM4J project') and immediately scopes it with the auto-resolution behavior and auto-injected projectId. Any agent can distinguish it from qtm4j_update_test_cycle, qtm4j_search_test_cycles, and qtm4j_create_test_case without opening a schema.

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?

Provides a hard prerequisite (set_project_context must be called first, never auto-select a project) and explains folder-resolution behavior with explicit instructions on how to obtain a folderId. Clear context for use, though it never names a sibling alternative (e.g. 'to modify an existing cycle use qtm4j_update_test_cycle').

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

Deploy Server

Other Tools