screenshot

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

With no annotations, the description carries the full burden and does substantial work: it discloses the capture source (HDMI input), the encoding (JPEG), the internal settle-until-stable behavior bounded by ARKKVM_SETTLE_MAX_MS, and the side effect that mouse coordinates are tied to the latest screenshot. Gaps remain around failure modes (no signal / disconnected HDMI) and whether the capture is blocking.

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?

Front-loaded one-line purpose followed by two tight parameter notes, each of which adds decision-relevant information rather than restating the schema. 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?

For a two-parameter tool with no output schema, the description covers capture semantics, output format, parameter behavior, and the coordinate-space contract. What's missing is error/edge behavior (no HDMI signal, timeouts) and any explicit statement of how mouse coordinates relate to a downscaled max_width.

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 and it does: max_width is explained (downscale target, 0 = native resolution — critical since the schema default is 1280), and wait_ms is explained as an extra pre-capture delay that is rarely needed because the tool already waits for the picture to stabilize.

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 target computer's screen (HDMI input)') plus the output format (JPEG). It also implicitly distinguishes itself from the mouse/input siblings by declaring that they operate in the coordinate space of the most recent 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?

Gives clear operational context: the coordinate-space dependency tells the agent a screenshot must precede mouse actions, and it explicitly advises that wait_ms is 'rarely needed' because of built-in settling. It stops short of naming when not to use the tool or listing explicit alternatives, but the usage picture is unambiguous.

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