take_screenshot

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

The description clearly states that mode 'app' works even when the window is behind others (minimized excepted) without raising it or taking focus, while 'region' and 'window' require user interaction. It also reveals the returned image is scaled down while the file keeps full resolution — useful details not visible from schema or annotations. Missing a small amount of detail about clipboard/editor side effects, but for a screenshot tool this is strong disclosure.

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?

The description is a paragraph but every sentence earns its place. It front-loads the core action and then advances through modes, preferences, annotation flow, path handling, and resolution behavior without fluff.

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?

Given the tool is action-oriented with no output schema and a rich set of 7 parameters, the description covers when to use each mode, how to feed the capture into annotate_screenshot, the practical distinction between scaled image and original file, and explicit choice support for real agent scenarios.

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?

The schema already explains enum values, so the description adds meaning where schema is thin: it clarifies the interaction behavior for each mode, how 'app' and 'title_contains' interplay, and what annotate/path/clipboard do beyond their one-line schema descriptions. With 86% schema coverage, the description goes beyond baseline 3 rather than merely repeating schema.

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 names the verb ('Capture the screen and return the image') and specifies four distinct modes with concrete behaviors. It clearly distinguishes the tool from siblings like annotate_screenshot and extract_text by explaining when the capture is returned versus handed to the drawing editor.

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?

The description gives explicit guidance: prefer mode 'app' when the user asks about a particular program, and use annotate=true when the user wants to mark the shot themselves. This creates a clear decision tree rather than just listing features.

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