capture_desktop_screenshot

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

With no annotations, the description carries the full burden and delivers well: it details the return as text metadata plus MCP image content, clarifies save_path only adds a disk copy, explains return_base64 is opt-in, and specifies that width/height/left/top are physical screen pixels matching mouse_click's coordinate range unscaled. This is substantive behavioral context beyond a one-line summary.

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?

Every sentence adds value: the primary behavior, the non-page-screenshot distinction, parameter side effects, and the critical coordinate-system note for pixel mapping. It is dense but efficient, with no filler.

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?

No output schema exists, so the description explaining the returned metadata and MCP image content is essential and provided. It also covers save behavior, base64 opt-in, and coordinate semantics, making the tool fully usable by an agent without external assumptions.

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 0%, so the description must compensate. It clarifies save_path's side effect ('only adds a disk copy') and return_base64's opt-in nature. These add meaning beyond the raw schema. The description does not fully elaborate return_base64's output format, but for two simple optional params this is adequate compensation.

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 states a precise verb and resource: capture the complete visible virtual desktop across all displays and return text metadata plus MCP image content. It also explicitly distinguishes itself from a background-tab screenshot, which separates it clearly from capture_page_screenshot.

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 makes the scope explicit ('complete visible virtual desktop across all displays') and provides an exclusion ('this is not a background-tab screenshot'), which tells the agent when not to use this tool. It does not name an alternative tool directly, but the intended usage is clear enough from the scope and the sibling list.

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