Skip to main content
Glama
SmartBear

SmartBear MCP server

Official
by SmartBear

Zephyr: Create Test Case Steps

zephyr_create_test_case_steps
Destructive

Add or replace test case steps in Zephyr with inline instructions or calls to another test case. Select APPEND to add steps or OVERWRITE to replace existing steps.

Instructions

Create steps for a Test Case in Zephyr. Supports inline step definitions or delegating execution to another test case (also known as 'call to test' via UI). Requires a mode: APPEND adds steps to the end of the existing list, OVERWRITE deletes all existing steps and replaces them with the provided ones. Always ask the user to choose between OVERWRITE or APPEND before calling this tool.

Toolset: Test Cases

Parameters:

  • testCaseKey (string) required: The key of the test case. Test case keys are of the format [A-Z]+-T[0-9]+

  • mode (string) required: Valid values: "APPEND", "OVERWRITE". OVERWRITE deletes and recreates the test steps and associated custom field values using the provided input. Attachments for existing steps are kept, but those for missing steps are deleted permanently APPEND only adds extra steps to your test steps.

  • items (array) required: The list of test steps. Each step should be an object containing inline or testCase. They should only include one of these fields at a time.

Examples:

  1. To the Test Case SA-T1, add steps that will test a login page.

{
  "testCaseKey": "SA-T1",
  "mode": "APPEND",
  "items": [
    {
      "inline": {
        "description": "Navigate to the login page",
        "expectedResult": "Login page is displayed"
      }
    },
    {
      "inline": {
        "description": "Enter valid credentials and click Submit",
        "expectedResult": "User is redirected to the dashboard"
      }
    }
  ]
}

Expected Output: The ID of the Test Steps resource and the API self URL to fetch it

  1. To the Test Case MM2-T15, replace all existing steps with new ones that test the settings page for an Admin user.

{
  "testCaseKey": "MM2-T15",
  "mode": "OVERWRITE",
  "items": [
    {
      "inline": {
        "description": "Open the settings page",
        "testData": "User role: Admin",
        "expectedResult": "Settings page is accessible"
      }
    },
    {
      "inline": {
        "description": "Change the notification preference",
        "testData": "Preference: Email only",
        "expectedResult": "Notification preference is updated successfully"
      }
    }
  ]
}

Expected Output: The ID of the Test Steps resource and the API self URL to fetch it

  1. To the Test Case SA-T1, add a step that reuses the steps from the Test Case PRJ-T42

{
  "testCaseKey": "SA-T1",
  "mode": "APPEND",
  "items": [
    {
      "testCase": {
        "testCaseKey": "PRJ-T42"
      }
    }
  ]
}

Expected Output: The ID of the Test Steps resource and the API self URL to fetch it

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
modeYesValid values: `"APPEND"`, `"OVERWRITE"`. <br> `OVERWRITE` deletes and recreates the test steps and associated custom field values using the provided input. Attachments for existing steps are kept, but those for missing steps are deleted permanently <br> `APPEND` only adds extra steps to your test steps.
itemsYesThe list of test steps. Each step should be an object containing `inline` or `testCase`. **They should only include one of these fields at a time**.
testCaseKeyYesThe key of the test case. Test case keys are of the format [A-Z]+-T[0-9]+

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
idNoThe ID of the entity
selfNo
Install Server

TDQS

A4.4/5.0
Behavior5/5

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

Annotations already mark the tool as destructive, and the description adds critical specifics: OVERWRITE deletes existing steps and associated custom field values, and attachments for missing steps are deleted permanently. It also warns that APPEND only adds steps. This goes well beyond the annotation and gives the agent the risk context needed for safe invocation.

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 longer than average but well structured with bold parameter headers, clear mode definitions, and three practical examples for the non-trivial inline/testCase item structure. The critical destructive mode warning and user-confirmation instruction are front-loaded. It is appropriately sized for the complexity of the items parameter.

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?

The description covers required parameters, both modes, destructive consequences, the two item variants, the user-confirmation requirement, and the expected output (step resource ID and API self URL). Combined with the rich input schema, no critical information appears to be missing for an agent to invoke the tool correctly.

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

Parameters3/5

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

Schema description coverage is 100%, so the baseline is 3. The description largely repeats the schema's parameter documentation: key format, mode semantics, and the inline/testCase mutual exclusivity. The examples are helpful but do not add new parameter-level meaning beyond what the schema already provides, so no higher score is warranted.

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 opens with a specific verb and resource: 'Create steps for a Test Case in Zephyr.' It also clarifies the two supported step forms (inline definitions and delegation to another test case), which distinguishes this from read-only or execution-step tools. The naming and description together leave no ambiguity about what the tool does.

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 explicitly requires the user to choose between OVERWRITE and APPEND and instructs the agent to always ask before calling. It explains exactly what each mode does, which serves as a clear selection guideline. It does not name sibling alternatives for other step operations, so it stops short of full tool-level routing, but the mode guidance is strong.

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

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