Look at the screen

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

Annotations only declare readOnlyHint=true, so the description carries the behavioral load and does it well: it discloses the default capture target, the terminal fallback, and the screen-vs-window mode. It does not describe failure modes (e.g., missing permission, no matching window) or image format/size, leaving a modest gap.

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 sentences, front-loaded with the core action and return type, followed by default behavior and the optional targeting modes. No filler or restatement of the tool name.

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 five parameters are optional and fully schema-documented, and there is no output schema — the description correctly states the return is an image. Defaults and targeting modes are covered; only cross-tool routing and error behavior are absent, which is minor given the schema richness.

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 on top: it explains the interaction between target and display, and the fallback semantics of under_cursor that the schema only hints at. That is genuine value beyond the structured fields.

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 — 'Take a screenshot of what the user is looking at and return it as an image' — which is concrete and unambiguous. It does not, however, distinguish itself from nearby siblings like device_screenshot or select_region, so it loses the top mark.

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 clear operational context: default captures the window under the mouse, terminal falls back, target 'screen' captures the whole display, and a window can be picked by app/title or id. It never says when to prefer this over device_screenshot or select_region, so it stops short of explicit alternatives.

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