screenshot

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

Annotations already establish the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds real context beyond them: the output is PNG, captured windows are included even when occluded, and image pixels map 1:1 to screen points, with the offset rule for window captures. It omits anything about screen-recording permissions or where the image is returned, keeping it short of a 5.

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 dense sentences with no filler. The capture modes come first and the coordinate-mapping caveat that an agent most needs before clicking comes second — well front-loaded.

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?

With no output schema, the description is responsible for the return contract and does explain the image format and coordinate mapping. The one remaining gap is how the captured image is delivered (path vs inline data), which an agent would want to know, but everything needed to invoke it correctly is present.

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 description coverage is only 20% (just 'app'), so the description carries most of the semantic load. It names the region group '(x, y, w, h)', implies omission selects the main screen, and explains the app parameter's role as the front window target, which meaningfully compensates for the bare schema entries.

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 (Capture) plus resource (PNG) and enumerates the three capture scopes: main screen, region (x,y,w,h), or an app's front window. An agent immediately knows this produces an image and which modes exist, distinguishing it from the interaction siblings like click, drag, and type.

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?

No alternative screenshot tool exists to route against, but the text does give useful workflow context: 'even if other windows cover it' and the instruction to add the reported origin to get screen coordinates for click. That is implied usage guidance rather than an explicit when/when-not statement.

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