build.run_unit_tests

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

No annotations are provided, so the description carries the behavioral disclosure burden. It opens with '[approval required][workspace write][network][risk:dangerous]', which clearly signals side effects, permission requirements, and risk. It does not detail which workspace files may change, but the explicit danger and network flags provide substantial transparency beyond the schema.

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 one compact sentence, with the risk and approval flags front-loaded. Every part contributes directly to safe invocation and understanding, with no filler or repetition.

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?

The description covers purpose, supported platforms, and risk profile, which is a strong baseline for a simple one-parameter tool. However, it omits the default behavior when `kind` is not provided and gives no indication of command output or return value, which matters because there is no output schema to fill that gap.

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?

The schema has one parameter with 0% description coverage, so the description must compensate. It lists the supported frameworks, which mirrors the enum values in the schema, but it never names the `kind` parameter, explains that it is optional, or describes what happens when it is omitted (e.g., auto-detection). The description adds little semantic value beyond restating the enum.

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 action ('Run unit tests') and enumerates the supported project types ('Flutter, React Native, or Android'), which clearly distinguishes it from sibling build commands like build.run_lint and build.build_debug_apk. The scope is immediately understandable and not a tautology of the tool name.

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?

There is no explicit guidance on when to use this tool versus alternatives. The description implies it is for unit testing on the listed platforms, but it does not mention conditions, prerequisites, or exclusions such as 'use build.run_lint for static analysis' or 'run after install_dependencies.' The usage context is left to inference.

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