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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=true, so the safety profile is covered. The description usefully adds that capture happens against the DRAFT in a real browser and that `selector` produces an unscaled full-size render, but it never says what the tool returns (image payload, URL, artifact id) or flags the latency/async nature of real-browser captures.

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?

Two tight sentences, front-loaded with the action and scope, then the rendering caveat and selector/width advice. Dense but never padded; minor friction from shorthand like '390' without units and a heavy em-dash list.

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?

All six parameters are documented in the schema and the read-only safety profile is covered by annotations, so nothing essential is missing for invocation. However, with no output schema the description should say what a screenshot call yields (and whether it is synchronous or polled), which it omits.

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 description genuinely adds meaning: `selector` yields full-size (not scaled down) section captures, and it recommends concrete widths ('design width and 390') that the numeric `width` parameter alone does not convey as intent.

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 (screenshot) and resource (the DRAFT site) rendered 'in a real browser', and clarifies what that actually captures: compiled CSS, theme, state-driven UI, responsive layout. No sibling tool performs rendering/capture, so an agent can distinguish it immediately.

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?

Frames the tool as 'the only way to see compiled CSS, theme, state-driven UI and responsive layout', which tells the agent when this is the right call, and advises targeting sections with `selector` and shooting at design width and 390. It stops short of naming exclusions (e.g. published vs draft, or what to use for non-visual verification).

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