windows_screenshot

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive). Beyond that, the description discloses two useful traits: the PNG is returned to the client, and a copy is persisted under screenshots/ — a side effect not visible in the schema. It stops short of noting behaviors like occlusion/foreground requirements or failure when a window is missing.

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 sentences, zero filler, and the core capability is front-loaded before the return/persistence note. Nothing is repeated from the title or schema.

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 and zero required parameters, the description supplies the missing return-channel information (PNG returned and saved to screenshots/). It is nearly complete; the only unaddressed items are error/edge conditions such as a nonexistent pid or a minimized window.

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% and both parameters carry their own descriptions, so the schema does the heavy lifting. The description only echoes the pid/title alternative selection ('selected semantically by pid/title') without adding format or precedence detail beyond what the schema states.

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 ('Capture the visible bounds of a native Windows application window') and names the selection mechanism (pid/title). The qualifier 'native Windows application window' cleanly separates it from browser_screenshot, chrome_screenshot, and windows_snapshot.

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 word 'native' implicitly signals when this tool applies instead of the browser/chrome screenshot siblings, and the pid reference to windows_list hints at a prerequisite. However, it never explicitly says when to choose this over browser_screenshot or record_clip, nor states any exclusion or ordering requirement.

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