system_get_active_window

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

Annotations already cover the safety profile (readOnly, non-destructive, idempotent, openWorld). The description adds genuinely non-derivable context: the read happens via the Accessibility API and requires the accessibility permission, which tells the agent why calls may fail or prompt.

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?

One dense sentence plus a compact metadata bracket, with the purpose front-loaded. Every clause earns its place: verb, resource, mechanism, and prerequisites.

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?

With an output schema covering return values and annotations covering safety, the description only needs to name the resource and prerequisites, which it does. It stops short of noting behavior when no window is focused, but the essentials for calling correctly are present.

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 of 4 applies and the schema has nothing to document. The description's mention of what is retrieved (title and geometry) is a scope note rather than parameter guidance.

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+resource: reads the frontmost focused window's title and geometry. The word 'window' (vs 'app') gives an agent enough to distinguish it from system_get_frontmost_app, though it never explicitly names that sibling or system_list_windows as the non-focus-wide alternative.

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 when-to-use or when-not guidance is given. Although the purpose implies its use, there is nothing telling the agent to prefer this over system_get_frontmost_app or system_list_windows, and no failure conditions are mentioned beyond an implied permission prerequisite.

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