screenshot

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

Beyond the readOnlyHint annotation, the description discloses meaningful runtime behavior: it tries gnome-screenshot, scrot, imagemagick 'import', and grim (Wayland) in order. It also explains the two return modes depending on return_image. This is useful behavioral context that annotations alone do not provide.

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 compact, front-loaded with the core purpose, and organized into clear Args and Returns sections. Every sentence adds information: purpose, fallback behavior, parameter list, and return type. No filler or redundancy.

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?

For a simple screenshot tool, the description covers purpose, dependencies, parameters, and return value. Since there is no output schema, explaining the Image | str result is necessary and provided. It could be more complete by noting failure behavior when no screenshot tool is available and what happens if save_path is omitted, but it is adequate for an agent to invoke the tool correctly.

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 description lists save_path, window, and return_image, and crucially explains how return_image changes the result type. The schema already documents each property, so the description adds conditional return behavior rather than repeating schemas. It could say more about window support across backends, but it does not merely restate the 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 opens with 'Kepernyokep keszitese a lokalis asztalrol' — a clear verb and resource, stating exactly what the tool does: take a screenshot of the local desktop. This is distinct from sibling tools like window_list, desktop_ocr, and system_info. No ambiguity remains about the tool's core function.

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 purpose implies when the tool should be used — whenever a screenshot is needed — but the description never explicitly states alternatives or conditions. It does not mention 'use this instead of desktop_ocr for image capture' or any when-not-to-use guidance. The fallback-order line is about implementation, not usage selection.

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