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

Goes well beyond the annotations (readOnlyHint=false, destructiveHint=true, openWorldHint=true) by disclosing that the run is queued and returns a runId immediately, that content/soak/chaos/full change what the screen plays while running, and that these same suites additionally require `screen.cast` on top of `screen.edit`. This surfaces the destructive side effect and the extra permission requirement that annotations alone cannot express.

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-loads the action, then the suite catalogue, then async behavior, then access restrictions — a logical order with no filler sentences. It is dense and somewhat wall-of-text, but each clause carries operational 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?

With an output schema present, return-value explanation is unnecessary, and the description nonetheless covers the async return contract, suite-specific access limits, permission prerequisites, and the competing single-frame tool. Nothing needed to call this correctly is missing.

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 100%, so the baseline is 3, but the schema's own suite description defers to this text ('see the tool description'), and the description supplies real semantic content for each enum value (what 'smoke', 'chaos', 'content', 'requirements' actually do). screenId gains only marginal added 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 and resource ('Start an automated Device Lab test suite against a connected player') and explicitly distinguishes itself from the sibling capture_device_frame ('For one screenshot use capture_device_frame instead'). An agent can identify the tool without opening the 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?

Gives explicit conditions per suite variant ('chaos' and 'full' only on internal workspace or test-device screen; 'requirements' for internal workspaces), names the follow-up tool to poll (get_device_test_run), and routes single-frame needs to an alternative. When-to-use and when-not-to-use are both covered.

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