Skip to main content
Glama

write_test_case

Document a test case with title, steps, and expected results; index it for search, and auto-push to git. Check existing coverage before adding to avoid duplicates.

Instructions

Create a test case document, index it immediately, and auto-push to git.

    Call search_tests() first to check for existing coverage before adding
    a new test case.

    Side effects: creates tests/YYYY-MM-DD-{slug}.md in the docs path,
    indexes it into the vector store, and pushes to git if configured.

    Use after writing or modifying tests to make them discoverable.
    Status values: "pass", "fail", "blocked", "pending" (default: pending).

    Args:
        title: Short test case title (e.g. "User login with expired token")
        scenario: What is being tested and why (the test intent)
        steps: Step-by-step test procedure
        expected_result: What should happen when the test passes
        preconditions: Setup required before running the test (optional)
        actual_result: Observed result if already executed (optional)
        status: "pass", "fail", "blocked", or "pending" (optional)
        tags: Comma-separated tags, e.g. "auth,regression,critical" (optional)
        project: Target project name (optional)

    Returns:
        Saved filename, chunk count, and whether auto-push succeeded.
    

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNo
stepsYes
titleYes
statusNo
projectNo
scenarioYes
actual_resultNo
preconditionsNo
expected_resultYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes
Behavior5/5

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

Discloses side effects: file creation with specific naming, vector store indexing, and git push. No annotations provided, so description carries full burden; it fully informs the agent of all behavioral impacts.

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?

Well-structured with sections (purpose, usage, side effects, args, returns), but contains minor redundancy (status values mentioned twice). Still efficient and easy to parse.

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 tool's complexity (9 parameters, side effects, output), the description fully covers all aspects. Output schema exists and return values are described. No gaps remain.

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 has 0% description coverage, but the description explains all 9 parameters, including defaults, status enum values, and optional nature. Adds significant meaning beyond schema types/titles.

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?

Clearly states the tool creates a test case document, indexes it, and auto-pushes to git. Distinct from sibling write tools (e.g., write_api_doc) by specifying test case creation and its unique side effects.

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

Usage Guidelines5/5

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

Explicitly advises calling search_tests() first to check coverage, and states the tool should be used after writing or modifying tests. Provides clear when-to-use context and implies alternatives (search_tests).

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/dl4rce/flaiwheel'

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