pointer_info

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

Since no annotations are provided, the description carries the full behavioral burden, and it delivers: it discloses that screen_width/screen_height cover only the primary display while screen_bounds spans the virtual desktop, and that output is in physical not CSS pixels. The verb 'Report' clearly signals a non-mutating query. It lacks only minor details like whether the position is sampled live or cached.

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?

Three sentences with zero waste. The core purpose is front-loaded in the first sentence, the second sentence resolves the primary-vs-virtual display ambiguity, and the third sentence prevents a common unit confusion with page_* tools. Every sentence earns its place.

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?

The output schema documents return values, and there are no parameters, so the remaining burden is coordinate semantics—which the description fully addresses. It explains physical vs CSS pixels, primary vs virtual desktop, and the interaction with mouse_click's accepted range. Nothing an agent needs to correctly call and interpret this tool is missing.

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 tool has zero parameters, so the baseline is 4 per the rubric. The description adds further value by explaining the semantics of the returned fields (screen_width/screen_height vs screen_bounds), which helps the agent interpret the output schema correctly even though no argument documentation is needed.

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 (Report), resource (desktop mouse position and screen geometry), and the critical unit qualifier (PHYSICAL pixels). The distinction from page_* tools which use CSS pixels separates it from sibling tools that also deal with coordinates. An agent can immediately understand what this tool returns and how it differs from page-level coordinate tools.

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 explicitly excludes page_* tools as alternatives by noting they use CSS pixels, and tells the agent that screen_bounds is the range mouse_click will accept—implying pointer_info should be consulted before clicking. This provides clear context for when to use it, though it stops short of explicitly stating 'call this before mouse_move/mouse_click' or naming the exact alternative conditions.

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