List Test Cases

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

No annotations are provided, so the description carries the full burden. It conveys the essential read-only listing behavior and mentions pagination and filtering, but these facts mostly restate what the schema already documents (limit, offset, filter parameters), and it does not disclose defaults such as whether draft test cases are returned by default or how multiple filters combine. The low-risk nature of a read-only list tool partially offsets this thinness.

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?

Three short sentences (~30 words) with the purpose front-loaded and no filler. The second sentence is slightly redundant with the schema's pagination/filter parameters, but it aids quick capability scanning, and the get_project hint earns its place as cross-tool guidance.

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?

For a 15-parameter tool with nested objects and an output schema present, the description delivers adequate high-level orientation and a useful sequencing hint, and return shapes are covered by the output schema. However, it lacks guidance on how filters combine and does not route users to get_test_case for single-case lookups, which would be valuable at this complexity level. Some additional orientation would push this higher.

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?

Schema description coverage is 100% and the parameter descriptions are rich (e.g., 'Use 0 to fetch only the total count', the customFields format caveat, sortOrder requiring sortField). The description adds only the generic phrase 'various filtering options,' which does not exceed what the schema provides, so the baseline 3 applies.

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?

States a specific verb ('List') and resource ('test cases from a project in QA Sphere'), and the phrase 'Supports pagination and various filtering options' clarifies the listing scope. It does not explicitly differentiate from siblings like get_test_case or list_test_cases_tags, which prevents a 5.

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 closing sentence provides actionable sequencing guidance: 'Usually it makes sense to call get_project tool first to get the project context.' This is genuine usage advice, but there is no when-not-to-use guidance or explicit comparison with alternatives such as get_test_case for a single case or list_test_cases_tags for tag-focused listing, so routing between siblings is left to inference.

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