Skip to main content
Glama
SmartBear

SmartBear MCP server

Official
by SmartBear

QTM4J: Get Automation History

qtm4j_get_automation_history
Read-onlyIdempotent

Retrieve paginated history of automation result uploads to review import status, audit CI/CD uploads, and paginate through past records.

Instructions

Retrieve a paginated history of past automation result uploads for a QTM4J project.

Toolset: Test Automation

Parameters:

  • startAt (number): Zero-indexed starting position for pagination (default: 0). (default: 0)

  • maxResults (number): Maximum number of records to return per page (default: 20, max: 100). (default: 20)

Output Description: Paginated list of automation import history. Each record includes: format, processStatus, importStatus, startTime, endTime, trackingId, detailedMessage, and a summary array. summary[0] contains: testCycleIssueKey, testCycleSummary, testCasesCreated, testCaseVersionsCreated, testCaseVersionsReused, testStepsCreated. Render as individual cards separated by dividers, NOT a table. Show '1–N of total' count above. Never show raw fileName.

Use Cases: 1. Review past automation result uploads for a project 2. Check the status of recent automation imports 3. Audit CI/CD automation upload history 4. Paginate through all historical automation uploads

Examples:

  1. Get the first page of automation upload history (default page size 20)

{}

Expected Output: Paginated list of automation history records with upload status and metadata

  1. Get the second page of automation upload history

{
  "startAt": 20,
  "maxResults": 20
}

Expected Output: Next 20 automation history records

  1. Get up to 50 records starting from the beginning

{
  "startAt": 0,
  "maxResults": 50
}

Expected Output: Up to 50 automation history records

Hints: 1. NO PROJECT CONTEXT REQUIRED: Do NOT call set_project_context and do NOT ask the user for a project key, project ID, or any other project details. This tool works independently. 2. PAGINATION: startAt is zero-indexed (default: 0), maxResults controls page size (default: 20, max: 100). Increment startAt by maxResults to fetch the next page. 3. Returns an empty data array (not an error) when no history records exist. 4. DISPLAY FORMAT: Show '1–N of ' above all cards. Render each record as a card separated by --- dividers. Each card has two sections:

PRIMARY SECTION (always first): heading with status emoji (✅ SUCCESS / ❌ FAILED) + test cycle key and name; then format, start→end time, message, summary stats (test cases/versions created/reused/test steps), tracking ID.

EXTRA DETAILS SECTION (at the bottom of the card, under a 'Details' sub-label): any remaining non-null fields from the record such as fileSize, extraAttributes values, etc.

Skip any field that is null, missing, or false. NEVER show the raw fileName. NEVER use a table.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
startAtNoZero-indexed starting position for pagination (default: 0).
maxResultsNoMaximum number of records to return per page (default: 20, max: 100).

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
dataNo
totalNo
startAtNo
maxResultsNo
Behavior4/5

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

Annotations (readOnlyHint, idempotentHint, destructiveHint) already cover safety and idempotency. The description adds pagination details, emptiness handling, and display format. It doesn't mention rate limits or authentication, but the added context is valuable.

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?

The description is verbose with repeated defaults and extensive display formatting hints. While well-structured, it could be more concise. The examples and hints are helpful but lengthy.

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?

Given the complexity of pagination and history, the description covers input, output, behavior, error handling (empty array), and provides examples. Although there's an output schema, the summary ensures completeness.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% with good descriptions. The description reinforces defaults (0, 20), maxResults max (100), and explains pagination increment. This adds clear meaning beyond the schema.

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?

The description clearly states 'Retrieve a paginated history of past automation result uploads for a QTM4J project.' It specifies the verb (Retrieve), the resource (automation history), and distinguishes from upload siblings like qtm4j_upload_automation_result.

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?

The description includes four explicit 'Use Cases' and a 'Hints' section that says 'NO PROJECT CONTEXT REQUIRED' and not to call set_project_context. However, it does not directly compare with other history or status tools, missing some nuance.

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

Install Server

Other Tools

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/SmartBear/smartbear-mcp'

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