create_test_case

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

The description goes well beyond the annotations by disclosing side effects: tags are auto-created, folders/suites are auto-created when needed, and status/priority silently fall back to project defaults if omitted. It also states that the full created case object including shareUrl is returned. This gives the agent a strong model of what will happen at runtime.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long, but the tool is complex and almost every sentence earns its place: the suite constraint, the two creation paths, auto-creation behaviors, return value, tag behavior, and project defaults. It is organized with parenthetical labels and an 'IMPORTANT' callout, making the density digestible.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 13 parameters, no output schema, and no behavioral annotations, the description is remarkably complete: it explains return shape, required placement, alternate creation modes, auto-creation side effects, default-value behavior, and tells the agent where to look for project-specific vocabulary. The external link rollback behavior is also covered in the schema's nested parameter description, so nothing critical is missing.

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

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

The input schema already documents all parameters at 100% coverage, so the baseline is 3. The description adds decision-level meaning on top: which parameter branch to choose, what gets auto-created, and the important behavior of omitting status/priority. This is meaningful guidance beyond the schema, though the schema itself is already quite descriptive.

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

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific verb and resource: 'Create a new test case in a test suite.' It clearly distinguishes creation from related utilities like update_test_case, delete_test_case, and move_test_case. The nuance that test cases must live inside a suite is front and center.

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

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

The description explicitly explains the two mutually exclusive ways to call it: via folderId or via projectId with folderName/suiteName. It also tells the agent when to consult get_project for project-specific status/priority defaults. It does not explicitly contrast with update_test_case, but the create vs. update semantics are clear enough.

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