Run the autotest locally

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

Adds substantial behavior beyond the annotations: file side effects ('writes screenshots and report.json to a temp folder'), a duration warning with progress notifications ('takes a while'), a no-login auth note, and the shape of the result (pass/warn/fail plus failed checks with fixes). The write-to-temp-folder detail is consistent with readOnlyHint=false and non-destructive, and the no-progress-fast caveat is exactly the kind of operational context annotations cannot convey.

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?

Front-loaded with the action and scope, and every clause carries information: checks, viewports, ordering advice, side effects, duration, return shape. It is a single dense run-on paragraph heavy with parentheticals and semicolons, which costs a bit of scannability, but there is no filler to cut.

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-step local test runner with four params, an output schema and annotations, the description covers the prerequisites (none/login), side effects, latency, and result interpretation that an agent needs to call it correctly, and it correctly does not re-document the return schema in detail. Nothing material is left to inference.

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 all four parameters (dir, build, images, backendHosts) are already documented at the schema level, which sets the baseline at 3. The description reinforces only one of them ('unless build:false') and alludes to images via 'key screenshots as images', adding no syntax or edge-case meaning beyond the 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+resource ('Builds ... and runs the full Gamealia autotest locally') plus scope detail that separates it from siblings: headless Chromium, desktop 1280x720 and mobile 390x844, and the enumerated check list (SDK lifecycle, blank screen, input response, ads, console errors, static security analysis). An agent can distinguish it from gamealia_build, gamealia_check_integration and gamealia_upload_version without opening any 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?

Explicitly routes ordering: 'Run it before gamealia_upload_version, which repeats it on the server,' which both names the alternative and explains the redundancy, plus 'No login' tells the agent no auth step is needed first. It stops short of stating when NOT to run it (e.g. skip after a successful local run) or pointing to gamealia_build/check_integration for partial checks, so it is strong but not fully exhaustive.

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