capture_editor_window

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

Annotations already state readOnly/non-destructive/closed-world, and the description adds what they do not: PrintWindow can yield blank or stale GPU content, screen mode requires a foreground window, covered edges are cropped, interior overlaps with other apps are rejected, and the tool neither focuses windows nor sends input. These failure modes and the absence of side effects are exactly the context an agent needs to avoid trusting a bad capture.

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?

Four dense sentences, each carrying distinct information, with the output promise front-loaded. It is tight, though the mode caveats pile up quickly and could be split for easier scanning.

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?

There is no output schema, and the description does state the return shape (inline PNG, original file, coordinate metadata) and the main trust caveats. What is missing is how to obtain a valid windowId and how the sizing parameters affect the result, which matters for a 4-parameter tool with 0% schema documentation.

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 has to carry the parameter burden, and it only partially does. It explains the two method values in behavioral terms, but it never covers maxWidth/maxHeight (defaults 1600x1200 with min/max bounds) or the windowId format (^\d+:\d+$). The phrase 'freshly discovered window' hints that windowId comes from a listing tool without saying so.

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 description gives a specific verb (capture) and resource (game/editor window) and states what comes back: an inline PNG plus original file and coordinate metadata. It reads differently from siblings such as list_editor_windows, focus_editor_window, and playtest_frames, but it never names those siblings or tells the agent how they relate.

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?

It gives real guidance on choosing between the two modes: 'window mode uses PrintWindow; GPU content may be blank/stale', while 'screen mode requires foreground'. It also warns 'Inspect the image before assuming it is usable.' It leaves out when to prefer this tool over playtest_frames or other capture paths, but the within-tool mode choice is clear.

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