get_test_summary

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

No annotations are provided, so the description carries the full behavioral burden and handles it well: it discloses the date default ('Defaults to today'), the limit bound ('max 200'), and pagination mechanics ('Use for pagination' via offset). The behavior is read-only by implication ('Get'), and no side effects are claimed; the only gap is silence on empty-result behavior when a test has no history.

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 statement is front-loaded in one tight sentence, followed by a compact Args block where each line earns its place with defaults, examples, or bounds. There is no filler, repetition of schema titles, or tangential information.

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 5-parameter read-only query with an output schema available, the description covers everything needed to invoke the tool correctly: required vs. optional params, formats, defaults, and pagination. The only omissions are minor — expected behavior for unknown test names and the exact shape of the summary payload, the latter being reasonably delegated to the output schema.

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 0%, and the description fully compensates by documenting all five parameters with added meaning: a concrete example for project ('PublicDashboard'), the exactness requirement for test_name, the YYYY-MM-DD format plus default for date, the 50/200 default/max bounds for limit, and the skip semantics for offset. This goes well beyond the bare schema titles.

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 opens with a specific verb-resource pair ('Get summary of a test across builds') and states the analytical purpose ('shows pass/fail history to detect flaky tests'). The cross-build scope clearly differentiates it from build-scoped siblings like get_build_tests and get_build_details.

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 stated purpose ('pass/fail history to detect flaky tests') gives clear context for when to invoke this tool, and the cross-build framing implies it is for historical analysis rather than single-build inspection. However, it never names alternative tools or states when not to use it, so it stops short of explicit exclusions.

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