cursor_position

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

With no annotations, the description carries the full behavioral burden. It discloses that the tool reports in both image and screen coordinates, which is useful. However, it doesn't mention that it's read-only (though obvious), nor the output structure, though an output schema exists. It adequately covers the main behavior but could add a note about no side effects or state changes.

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?

A single, concise sentence that front-loads the core action and covers both coordinate systems. No filler, no redundancy. Reads clearly and efficiently.

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 zero-parameter tool with a descriptive output schema (not shown), the description covers the essential purpose. It doesn't mention edge cases like whether the cursor must be within a window, but that's likely covered by the output schema. The description is complete for a typical query tool.

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 takes zero parameters, so the baseline is 4 per the rubric. No parameter explanation is needed. The description correctly focuses on the output rather than inputs, which is appropriate for a parameterless tool.

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 verb ('Report') and a clear resource (the pointer position), and specifies two coordinate systems (image and screen). This makes the tool's function immediately clear and distinguishes it from sibling tools like click or move, which are actions rather than queries.

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 implies the tool is used to get the current pointer location, but it does not explicitly say when to use it versus alternatives like screenshot or desktop_info. It also doesn't mention that it's a read-only query or that it's useful before other actions. Fine for a simple tool, but lacks guidance on when to choose this over siblings.

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