Zephyr: Get Test Cases

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

Beyond the annotations (readOnlyHint=true, idempotentHint=true, destructiveHint=false), the description discloses an important behavioral trait: the server may enforce a lower limit than requested, causing the result set to be truncated, and instructs the agent to 'Always check the limit value in the response.' It also explains that startAtId is zero-indexed for ID-based pagination. This adds meaningful behavioral context beyond what the annotations already communicate.

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 well-structured with headings for toolset, parameters, and examples, and the truncation warning is useful. However, the parameter section largely duplicates the schema descriptions, and the five examples are somewhat repetitive—each shows a similar pattern with one varying filter. This could be more concise, though the organization makes it easily scannable.

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 read-only, filtered list tool with an output schema present, the description covers all necessary invocation details: all optional filters, pagination parameters, defaults, truncation behavior, and illustrative examples. It does not describe the response structure, but the output schema exists and would carry that information. The description is sufficiently complete for an agent to call the tool correctly.

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%, so the schema already fully documents every parameter, including defaults, maximums, formats, and descriptions. The tool description repeats this information nearly verbatim rather than adding new meaning. The examples illustrate parameter combinations but do not provide additional semantic detail about the parameters themselves beyond what the schema already states. A baseline of 3 is appropriate.

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 states a specific verb and resource: 'Get details of test cases in Zephyr.' This clearly identifies the operation and the domain, and the plural 'test cases' helps distinguish it from the singular 'zephyr_get_test_case.' However, it does not explicitly state that it returns a list or paginated results, nor does it explicitly contrast itself with sibling tools like 'zephyr_get_test_case' or 'zephyr_get_test_case_steps.'

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 provides multiple examples showing how to filter by project, folder, pagination, and limit, which implies when an agent might want to use this tool. However, there is no explicit guidance about when to use this tool versus alternatives (e.g., 'for a single test case, use zephyr_get_test_case'), nor any mention of when this tool should not be used. The usage context is implied through examples rather than stated directly.

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