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

Annotations already declare readOnly, non-destructive, openWorld=false. The description adds real value beyond them: passwords are never returned, refs expire at the next look, screenshots are incurrable, and pagination is possible via cursor. This is meaningful behavioral disclosure despite annotations covering safety.

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 what the tool returns, then parameter notes. Efficient, though the parameter sentence has a slightly telegraphic style ('response_detail (summary|compact|full), fields (dotted paths), cursor (next page) — see the server instructions.') that pushes detail off-doc.

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?

No output schema, and 0% schema description coverage, so the description needs to do more. It covers return content, ref lifecycle, and three of four params, but omits the screenshot param's semantics, any pagination size/limit detail, and defers heavily to 'server instructions' the agent may not have.

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 0%, so the description carries the burden. It names three of four parameters with hints: response_detail (summary|compact|full), fields (dotted paths), cursor (next page). The screenshot parameter is never explained despite being listed in the element inventory. Partial compensation only.

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 first sentence states a concrete verb+resource: 'See the page or app you opened', followed by a precise inventory of what is returned (actionable elements with ref/role/name/box, headings, scroll, screenshot). This clearly distinguishes it from siblings like screen_act, screen_open, and media_look.

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?

Implied usage only: 'the page or app you opened' anchors it to prior screen_open/screen_open_app, and the ref-validity note implies re-look workflow. But it never explicitly contrasts with screen_act (see vs act) or screen_result, and does not give explicit when-not-to-use guidance.

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