windows_tool

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

With no annotations, the description carries the full burden of behavioral disclosure. It mentions operations like 'close', 'minimize', and 'launch' but does not disclose potential side effects, permissions required, or whether actions are reversible. It also omits critical context like what happens with screenshots (e.g., requires outputPath) or whether mouse/keyboard actions may disrupt the user's session. The catalog-style listing gives limited transparency beyond the operation names themselves.

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 extremely compact and well-organized, using category groupings (Keyboard, Mouse, Windows, Other) to present a large number of operations in a scannable format. Every sentence and fragment contributes meaning without fluff, making it easy for an agent to quickly grasp the tool's capabilities.

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 tool's complexity (18 operations, 20 parameters) and lack of output schema, the description provides a solid overview but leaves gaps. The 'cursor' operation is absent from the description despite being in the enum, and return values for operations like window_info or screenshot are not described. The schema covers parameter details, but an agent would struggle to know the exact expected inputs or outputs for several operations without additional information.

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%, with each parameter already having a description, so the schema carries the main semantic burden. The description adds a few inline details (e.g., modifiers, hotkey example, mouse buttons) but largely repeats what the schema already provides, so it provides marginal added value.

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 opens with 'Windows UI automation', clearly stating the tool's domain and purpose. It enumerates specific operations (keyboard, mouse, windows, other) that distinguish it from sibling tools like process_tool or clipboard_tool, making it immediately clear what this tool is for.

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?

The description provides no explicit guidance on when to use this tool versus alternatives, nor does it mention any exclusions or prerequisites. It simply lists operations without context on when each should be chosen over another tool, leaving the agent to infer usage from the operation names alone.

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