Maximize, minimize, restore or go fullscreen

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

Annotations only say readOnlyHint=false; the description adds meaningful behavior beyond that, noting fullscreen is a property while the others are methods, and warning that minimizing hides the window until restored. It does not say which window is affected (active vs. any) or whether the state persists, leaving a small 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?

Three short sentences, front-loaded with the action and states, followed by the property/method distinction and the one real gotcha. Nothing is redundant.

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 one-parameter mutation tool with no output schema and thin annotations, the description covers the state semantics and the main pitfall, which is enough to call it correctly. The only missing piece is which window is targeted.

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 100% and the single enum parameter is already fully documented, so the schema carries the load. The description restates the same four values and adds only an implementation nuance (property vs. method) rather than new semantic meaning about the parameter.

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 gives a specific verb+resource ("Change the window state") and enumerates all four states, so the agent knows exactly what the tool does. It does not explicitly distinguish itself from nearby siblings such as browser_set_window_size, browser_set_window_position, or browser_get_window_geometry, which an agent could easily confuse with it.

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 frames when to use it concretely ("the title-bar buttons and F11, done programmatically") and adds a real operational caveat: minimizing hides the window, so restore it before interacting. It stops short of naming an alternative sibling or stating exclusions relative to set_window_size.

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