mac_window

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

Annotations already declare destructiveHint=true, openWorldHint=true and idempotentHint=false, so the safety profile is covered. The description adds genuinely new behavioral context: every action is verified by re-reading the window, which tells the agent failures surface as observable state rather than silent no-ops. It does not say what happens on unresolvable windows or whether minimize/fullscreen state is reversible.

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?

A single dense sentence that front-loads the action list, then the window-selection mechanism, then the verification note. Parenthetical glosses keep it readable without extra filler, though the run-on format makes the per-action requirements harder to scan.

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 destructive, non-idempotent, 8-parameter tool with no output schema and no schema descriptions, the definition covers actions and target resolution but omits per-action parameter requirements and geometry semantics. Those gaps are exactly where an agent is most likely to call it wrongly.

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?

With 0% schema description coverage across 8 parameters, the description must carry the load, and it partially does: it maps x/y to move, width/height to resize, and explains the two window-selection modes. But it never states units or coordinate origin for x/y/width/height, nor which parameters are mandatory for which action, leaving significant ambiguity for a mutation tool.

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?

Names a concrete resource (a window) and enumerates the full action vocabulary — focus, raise, minimize, restore, move, resize, maximize, fullscreen, exit_fullscreen — which the schema does not encode since `action` is a bare string with no enum. It also distinguishes itself from the sibling `mac_windows` by naming it as the source of `window_id`.

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 a clear resolution rule: pick the window either by `window_id` (obtained from mac_windows) or by `app` + `window` as index or title. This establishes the prerequisite read-then-act workflow. It stops short of explicit exclusions, e.g. which sibling to use when the target window cannot be resolved.

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