Capture screenshot

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

Annotations only declare readOnlyHint and openWorldHint, but the description adds genuine behavioral context beyond them: the ghost cursor animates to the element first, and 'device' mutates the editor's responsive mode before the capture. It also discloses the return payload (image plus {box, bytes}), so the agent knows what it gets back.

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?

Three tightly packed sentences with the primary action front-loaded and no filler. Density is high — each clause carries new information (scope, side effects, return shape) — though the middle sentence stacks cursor behavior and device switching without much structural separation.

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 2-parameter, zero-required read tool this is complete: it covers capture scope, the responsive-mode parameter, side effects visible to the user, the recommended usage point, and the return value. Absence of an output schema is compensated by the explicit 'Returns the image plus {box, bytes}' note.

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 adds real meaning: it explains that omitting id captures the whole viewport, and that device changes the editor's responsive mode rather than merely labeling the output. That goes beyond the terse schema descriptions.

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 — a pixel-accurate PNG screenshot — and narrows scope to either one element (id) or the whole preview viewport, qualified by 'as rendered in the live editor'. That live-rendering qualifier implicitly separates it from structural siblings like inspect_element or get_canvas_skeleton, so an agent can pick correctly 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 a clear operational trigger: 'Use it after every meaningful mutation to verify the visual result instead of assuming it.' It does not state when to prefer a cheaper structural check (inspect_element) or any rate/cost exclusions, so there is clear context but no explicit when-not guidance.

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