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

Annotations cover the safety profile (readOnlyHint, openWorldHint, destructiveHint), so the bar is lower; the description still adds real behavioral context: per-device output contents, the inline side-by-side viewer the user sees, and a cost model ('Uses 1 credit per device'). It doesn't mention latency or failure modes of the check itself, but it adds meaningful disclosure beyond structured fields.

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?

Purpose is front-loaded in the first sentence, outputs follow, then usage guidance and cost. Four sentences each earn their place, though the viewer and credit notes could be trimmed slightly for efficiency.

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 read-only check tool with full schema coverage and no output schema, the description supplies everything needed: what it returns, what counts as 'wrong', when to use it, the sibling alternative, and the cost. No material gap remains.

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 each parameter already carries a description, so the baseline is 3. The description adds value by enumerating what 'what went wrong' means and by implying the per-device cost interacts with the multi-device 'devices' array, helping the agent reason about how many screenshots and credits a call yields.

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 ('Check whether a public web page looks right on phone, tablet and desktop') and enumerates concrete outputs (screenshots per device, sideways scrolling, JS errors, failed requests, broken images). It also distinguishes itself from the sibling 'screenshot' tool explicitly, so an agent can route without reading schemas.

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 concrete trigger conditions ('when the user asks whether a page looks right, works on mobile or has layout bugs, or after a deploy') and names the alternative sibling with its own selection condition ('To just see a page, including on one device, use screenshot instead'). Explicit when and when-not, with the alternative specified.

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