get_issue_test_coverage

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

With only readOnlyHint available, the description carries the behavioral burden and does so exceptionally: it discloses request cost (up to 2 per case), the dedup-before-cap ordering, unstable API ordering, lastResult null semantics ('never executed or run deleted', not 'untested'), the most-recently-CREATED selection rule that can surface older dates, fault-tolerant partial rows, 404 on unknown keys, and case-insensitive key resolution. This is far beyond what the annotation provides.

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?

Every sentence carries substantive information and the purpose plus cost model are front-loaded, but the whole definition is a single monolithic block with no visual grouping of the many distinct semantics (return shape, ordering, faults). Dense and largely waste-free, but readability suffers from the lack of structure.

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 multi-request, deduplicating, order-unstable tool with no output schema, the description supplies everything an agent needs: the return envelope, lastResult shape with omitted-key and null rules, edge cases (empty issues, 404, truncation note), and default behaviors. Nothing material is left undocumented.

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 coverage is already 100%, so the baseline is 3; the description earns extra credit by explaining that maxCases is applied AFTER duplicate links are collapsed (so it counts distinct cases) and by clarifying that includeLastResults=false omits the key entirely rather than nulling it. These interaction details are genuinely new, though most of the parameter content overlaps the already-rich schema.

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 and resource: a traceability report for a Jira issue covering every linked test case with its latest execution, and even names the underlying endpoints. It distinguishes itself from sibling tools by explicitly routing id-lookups to get_latest_result_for_test_case, so an agent can differentiate it without opening a schema.

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?

Names an alternative (get_latest_result_for_test_case) and the exact condition selecting it ('when you need the id'), plus the includeLastResults toggle for skipping execution reads. It gives clear operational context but does not explicitly contrast against the closely related get_test_cases_linked_to_issue sibling, so it stops short of full when/when-not coverage.

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