desktop_observe

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

With no annotations, the description carries the burden of behavioral disclosure. It does reveal key traits: it returns three artifacts and explains coordinate semantics. However, it leaves the meaning and lifetime of the '15-second snapshot ID' vague and says nothing about potential side effects or limitations.

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 two short sentences with the core output list front-loaded and no filler. Every phrase earns its place, and the coordinate-system note is placed at the end as a useful clarification.

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 observation tool with one optional parameter and no output schema, the description names the three returned artifacts and coordinate semantics, which is fairly complete. Gaps remain around max_width's effect and the purpose/lifetime of the snapshot ID, and no annotations help fill those gaps.

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 only parameter, max_width, is not explained anywhere; schema description coverage is 0%. The note about image-pixel coordinates does not clarify what max_width controls, so an agent must guess whether it limits screenshot width, layout dimensions, or something else.

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 specific action and resource: it returns a screenshot, window layout, and a 15-second snapshot ID. This makes its core purpose clear, though it does not explicitly contrast itself with siblings like desktop_inspect or desktop_windows.

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?

No guidance is given about when to use desktop_observe versus alternatives such as desktop_inspect, desktop_windows, or desktop_read_text. The only contextual note, 'Coordinates are image pixels,' is about output interpretation, not usage conditions.

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