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

Beyond the readOnly/non-destructive annotations, it discloses the polling requirement, the visibility scoping rule that makes out-of-location runs appear missing, and the trap that frameKey records a proof frame rather than a fetchable URL. These are exactly the behaviors an agent would otherwise get wrong.

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 core action, then four tight sentences covering polling, the frameKey caveat, the alternative tool, and the scoping rule. No sentence is filler.

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?

An output schema exists so return-value explanation is unnecessary, annotations cover the safety profile, and the description supplies the remaining operational context (poll loop, scoping, caveats). Nothing needed to invoke it 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% and the schema already documents runId as the '(dtr_…)' value returned by start_device_test_run, so the description adds no syntax or format detail beyond it. Baseline 3 for a fully documented single parameter.

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 ('Read a Device Lab run that start_device_test_run queued') and enumerates the returned payload (status, suite, device, summary, per-step pass/fail, expected vs observed, time taken). It clearly differentiates itself from start_device_test_run (the producer) and capture_device_frame (the screenshot path).

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 instructs to poll until the run has finished, routes screenshot needs to capture_device_frame, and explains the cross-location failure mode ('reads as not found'). Both when-to-use and the alternative path are stated outright.

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