list_child_windows

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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, so the safe read-only nature is established. The description goes further by specifying the exact return JSON structure, including the parent_hwnd, count, children fields, and that coordinates are relative to the parent window's top-left. This meaningful behavioral detail goes beyond the structured annotations.

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 concise and well-organized into summary, use-case, args, and returns. Every sentence contributes useful information, and it avoids redundant fluff. The structure makes it easy for an agent to quickly extract key usage details.

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 moderate complexity, the description covers the main input, output format, coordinate semantics, and a practical example. It does not mention whether child enumeration is recursive or only immediate children, nor what happens if the parent window is not found. These are notable but not critical gaps, so the tool remains mostly complete.

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?

The description summarizes the single parameter as 'the parent window by hwnd or title,' which adds some meaning beyond the empty top-level schema description. However, it omits the 'display' field (Linux-specific) and does not explain precedence between hwnd and window_title. The nested schema provides detailed field descriptions, so the parameter semantics are partially covered but not fully clarified by the tool description.

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 clearly states the tool's function: 'Enumerate the child controls of a window' and lists the included attributes (class, text, client rect, handle). It also gives a concrete example (finding the Edit control inside Notepad), which distinguishes it from sibling tools like list_windows that deal with top-level windows.

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 a clear use case: 'Useful for finding the exact control handle to target with background input' and mentions positioning for background clicks. It does not explicitly mention when not to use it or name alternative tools, but the guidance is contextual enough for an agent to select this tool appropriately.

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