Zephyr: Create Test Case Issue Link

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

Annotations already signal readOnlyHint=false and idempotentHint=false, which the description's 'Create a new link' aligns with. The description adds the expected output ('The newly created Issue Link with its ID and self link'), which is useful. However, it does not disclose what happens on duplicate links, whether missing test cases/issues cause failures, or any permission requirements — behavior an agent would want given the non-idempotent hint.

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 purpose is front-loaded in a single clear sentence, followed by well-labeled sections for toolset, parameters, and a worked example. The example earns its place by showing both parameters in context. Some redundancy exists since the parameter list duplicates the schema's descriptions, but overall the structure is efficient.

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?

With an output schema present, return values are structurally covered, and the description adds an 'Expected Output' note anyway. Purpose, parameters, example, and output are all addressed. The clear gaps are the absence of sibling differentiation from the other create-issue-link tools and the lack of duplicate/error behavior disclosure, which leaves a moderately complex linking operation slightly under-specified.

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 baseline 3 applies. The description restates the schema descriptions nearly verbatim for both parameters, adding little semantic value beyond the schema. The worked example is useful but flawed: it shows 'issueId': '10100' as a string, contradicting the schema's declared integer type, which could mislead an agent copying the example.

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 first sentence, 'Create a new link between an issue in Jira and a Test Case in Zephyr', states a specific verb and resource. It implicitly differentiates from the near-identical siblings zephyr_create_test_cycle_issue_link and zephyr_create_test_execution_issue_link by explicitly naming 'Test Case', but it never names those alternatives, so differentiation is left to inference.

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 gives no guidance on when to use this tool versus its close siblings (zephyr_create_test_cycle_issue_link, zephyr_create_test_execution_issue_link, zephyr_create_test_case_web_link). The example demonstrates how to call it but provides no decision rule, exclusions, or conditions for when this link type is appropriate over the others.

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