window

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

Annotations already declare this as a non-readonly, non-destructive, idempotent, closed-world tool. The description adds meaningful behavior beyond those annotations: restore places the window behind others, bottom moves it to the bottom of the z-order, close is a polite request that may trigger save prompts, and front requires consent.

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 dense but front-loaded with the core constraint, `without bringing it to the front`, followed by action definitions. It avoids filler and covers many actions in few sentences, though the single long paragraph is less scannable than a short action table would be.

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 7-parameter tool with no output schema and no schema descriptions, the description provides enough behavioral and action semantics to call most actions correctly, and annotations cover safety traits. It is incomplete mainly around how to identify the target window and what happens on invalid or missing window identifiers.

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?

Schema description coverage is 0%, so the description carries the burden and largely succeeds: it explains the action enum values, maps `x`/`y` to move, `width`/`height` to resize in screen pixels, and ties `foreground=true` to the `front` action. The notable gap is that the `window` target parameter, despite being central to invocation, is not described.

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 and resource: manage a window, with an explicit action list covering restore, minimize, maximize, close, bottom, front, move, and resize. It is clearly distinguishable from a generic UI tool, though it does not explicitly contrast itself with the sibling `windows` or `act` 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?

It gives useful action-specific context, especially that `front` requires `foreground=true` and the user's consent, while the default is to manage without bringing the window to the front. However, it does not say when to use this tool instead of siblings like `windows` for enumeration or `act` for broader interaction.

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