computer.get_active_window

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

With no annotations provided, the description carries the full burden of behavioral disclosure. It discloses the core behavior (read operation) but does not specify whether the tool has any side effects, performance implications, or failure modes (e.g., if no window is focused, or on different OSes). For a read-only tool, this is a notable gap.

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 a single, well-structured sentence that conveys the essential information in under 90 characters. It front-loads the action ('Get') and lists the exact output fields (title, application, process). There is no fluff or repetition.

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 tool with zero parameters and no output schema, the description covers the basic return values (title, application, process) adequately. However, it could be more complete by indicating the format of the output (e.g., a structured object or JSON) and any potential edge cases, but it is largely sufficient for a simple read-only 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 input schema is empty (no parameters), so there is no schema information to clarify. The description correctly implies no parameters are needed, which is unambiguous. The baseline for 0 params is 4 because the description is sufficient to understand the tool's inputs—there are none.

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 is precise: it specifies the verb 'Get' and the resource 'title, application and process of the currently focused window'—exactly what the tool does. It distinguishes itself from sibling tools like screenshot or get_ui_tree, which return visual or hierarchical data, not process metadata.

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 inspect the active window, but does not explicitly state when to use it versus alternatives. For example, it doesn't mention that get_ui_tree would be used to inspect deeper structural details, or that observe might be used for raw screenshots. However, given the tool's simplicity, the implied usage is fairly clear.

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