Detect regressions

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered. The description adds genuine behavioral information beyond that: results are grouped by the build/commit where tests first broke, and the analysis is threshold-based. It doesn't mention defaults or limits, but the schema carries those.

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?

Two sentences, both load-bearing. The qualifying criterion comes first and the grouping/output rationale second, so the agent gets the core behavior before any detail.

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 analytical tool with no output schema and fully documented parameters, the description covers what is detected and how results are organized. It could say a bit more about what to expect in the response shape, but nothing essential to correct invocation is absent.

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 each parameter already documents its meaning and default, so the baseline of 3 applies. The description adds no parameter-specific detail such as how min_stable_passes interacts with last_n, but nothing is missing that the schema doesn't already say.

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 ('Find tests') plus the exact predicate that qualifies a regression: stable-passing and now consistently failing. This cleanly distinguishes it from sibling tools like find_flaky_tests and get_failure_clusters, which target different failure patterns.

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 criterion ('stable-passing and now failing consistently') plus the grouping by breaking build gives a clear context for when this is the right tool. It stops short of explicitly naming alternatives or stating when-not to use it, so it lacks the exclusion clause that would make it a 5.

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