Close a window (self-guarded)

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

No annotations are provided, so the description carries the full burden. It discloses a key behavioral trait: the tool 'REFUSES to close this agent's own host terminal either way,' which is critical guard behavior. It also implies a fallback to the focused window when parameters are omitted. It does not mention failure modes or return values, but for a simple close action, the disclosed guard and selection behavior are sufficient.

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 sentences, each earning its place: the action and selection method, the critical guard, and the prerequisite. Information is front-loaded (action first), and there is no filler. The description is compact yet covers essentials.

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?

Given the simple nature of the tool (2 optional params, no output schema), the description covers what the tool does, how to select a target, the guard, and the prerequisite check. It doesn't specify failure behavior when no window matches or missing focused window, but that is a minor gap. Overall it provides a coherent picture for an agent to call correctly.

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 coverage is 0%, so the description must explain the parameters, and it does: it states selection 'by explicit address/match,' and clarifies that if omitted, the focused window is used. This gives meaning to both 'match' and 'address' beyond their raw schema names. It doesn't specify precedence or format, but for a typical tool it's sufficient. Sincest it says 'or' it implies either can be used.

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 ('Close') and resource ('a window') with explicit selection methods: by 'explicit address/match' or 'the currently focused window if omitted.' It also names a notable guard ('REFUSES to close this agent's own host terminal'), which makes the tool's scope unambiguous. While it doesn't name a specific sibling, it is clearly distinct from other window actions like window_focus or window_resize.

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?

Gives clear when-to-use guidance: 'Check window_list/desktop_status to pick a target first,' which sets a prerequisite and implies the tool is for closing already-identified windows. It does not explicitly state when not to use it or name alternatives, but the focus on selection via list/status is valuable context. Lacks an explicit exclusion of alternatives, hence not a 5.

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