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

Beyond the readOnlyHint annotation, the description discloses two important behavioral traits: the need to poll until terminal status and that screenshot URLs are short-lived and re-signed on each read, so they should be fetched rather than stored. This is valuable operational context the annotations do not provide.

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 compact and front-loaded: the core purpose is in the first sentence, followed by the essential polling behavior and the URL freshness warning. Every sentence conveys necessary information with no 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?

With only two well-documented parameters and no output schema, the description sufficiently covers what the tool returns (per-device results and screenshot URLs) and how to interact with it (polling, URL handling). Nothing critical is missing for an agent to use it correctly.

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%, with both template_id and preview_run_id clearly documented in the schema itself. The description adds no additional parameter-level detail, so the baseline score of 3 applies.

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 verb and resource: 'Get a preview run with its per-device results and screenshot URLs.' This clearly distinguishes it from sibling tools like create_preview_run or list_preview_runs by specifying the exact object and the unique content (per-device results, screenshot URLs) it returns.

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 description gives clear context for when to use the tool: to retrieve a preview run's results and to poll until status is COMPLETED or FAILED. It does not explicitly name alternatives or when-not-to-use conditions, so it misses the top tier, but the polling instruction provides actionable usage guidance.

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