Skip to main content
Glama
SmartBear

SmartBear MCP server

Official
by SmartBear

Zephyr: Get Test Case Steps

zephyr_get_test_case_steps
Read-onlyIdempotent

Retrieve test case step details from Zephyr by providing a test case key, with pagination options for large result sets.

Instructions

Get details of test case steps in Zephyr

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]+

  • maxResults (number): Specifies the maximum number of results to return in a single call. The default value is 10, and the maximum value that can be requested is 1000.

Note that the server may enforce a lower limit than requested, depending on resource availability or other internal constraints. If this happens, the result set may be truncated. Always check the maxResults value in the response to confirm how many results were actually returned. (default: 10)

  • startAt (number): Zero-indexed starting position. Should be a multiple of maxResults. (default: 0)

Examples:

  1. Get the first 10 test case steps for test case with key 'SA-T1'

{
  "testCaseKey": "SA-T1",
  "maxResults": 10,
  "startAt": 0
}

Expected Output: The first 10 test case steps with their details

  1. Get any test case step for test case with key 'SA-T1'

{
  "testCaseKey": "SA-T1",
  "maxResults": 1
}

Expected Output: One test case step with its details

  1. Get five test case steps starting from the 7th test case step of the list for test case with key 'SA-T1'

{
  "testCaseKey": "SA-T1",
  "maxResults": 5,
  "startAt": 6
}

Expected Output: The 7th to the 11th test case steps with their details

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
startAtNoZero-indexed starting position. Should be a multiple of maxResults.
maxResultsNoSpecifies the maximum number of results to return in a single call. The default value is 10, and the maximum value that can be requested is 1000. Note that the server may enforce a lower limit than requested, depending on resource availability or other internal constraints. If this happens, the result set may be truncated. Always check the maxResults value in the response to confirm how many results were actually returned.
testCaseKeyYesThe key of the test case. Test case keys are of the format [A-Z]+-T[0-9]+

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
nextNoURL to the next page of results, or null if there are no more results.
totalNoIndicates the total number of items available across all pages.
isLastNoIndicates if this is the last page of results.
valuesNoThe list of test steps
startAtYesIndicates the index of the first item returned in the page of results.
maxResultsYesIndicates the maximum number of results in this response. Note that the server may enforce a lower limit than requested, depending on resource availability or other internal constraints.
Install Server

TDQS

A3.6/5.0
Behavior4/5

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

Annotations already convey read-only, idempotent, non-destructive behavior. The description adds a genuinely useful caveat that the server may enforce a lower maxResults than requested and truncate results, and it instructs the caller to check the returned maxResults. This adds value beyond the annotations without contradicting them.

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 purpose is front-loaded and the content is organized into clear sections for parameters and examples. It is somewhat longer than strictly necessary because the parameter documentation duplicates the schema, but the examples are meaningful and well structured.

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?

With an output schema present and read-only annotations, the description covers the required key format, optional parameters, defaults, pagination, truncation behavior, and example calls. It does not explicitly explain ordering or how to choose between similar Zephyr get tools, but the essential context for calling this tool is present.

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 concrete examples and clarifies pagination semantics, including startAt as zero-indexed and the 7th-to-11th-step example. The 'get any test case step' example is slightly misleading because it actually returns the first result by default, preventing a perfect score.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

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: 'Get details of test case steps in Zephyr,' which clearly identifies the operation and distinguishes it from Zephyr tools that create, link, or retrieve execution steps. It does not explicitly name sibling alternatives, but the test-case-step resource is unambiguous.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no guidance on when to prefer this tool over alternatives such as zephyr_get_test_execution_steps or zephyr_get_test_case. The intended use is only implied by the name and first sentence; no exclusions, prerequisites, or alternative-selection criteria are provided.

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