sandbox_windows

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

Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered elsewhere. The description still adds a genuinely useful behavioral trait beyond that: hwnd values are only stable for the current state, warning that handles can go stale and should be re-discovered. It stops short of saying what 'visible' filters out or whether transient/minimized windows are excluded.

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 front-loaded sentence with no filler, which is appropriate for a no-argument discovery tool. The compressed hyphenated phrase 'stable-for-current-state' is the one spot where brevity shades into ambiguity.

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?

There is no output schema, so the description carries the burden of explaining what comes back, and it only says 'windows and hwnd values' without indicating whether titles, class names, z-order or counts are included. For a zero-parameter tool with no output schema this is the minimum viable, not 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 tool takes zero parameters, so per the rubric the baseline is 4 and there is nothing for the description to disambiguate. It correctly avoids describing nonexistent inputs.

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 (discover) and resource (visible guest windows) plus the payload it returns (hwnd values), which is enough to distinguish it from mutating siblings like sandbox_click or sandbox_exec. It does not explicitly contrast itself with overlapping siblings such as sandbox_inspect or sandbox_screenshot, and the phrasing 'stable-for-current-state hwnd values' is jargon-heavy enough to slow an agent down.

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?

No when-to-use guidance, no prerequisites, and no mention that the returned hwnds are the inputs other tools (e.g. sandbox_click, sandbox_text) expect. The agent must infer the tool's role purely from its name and requires this enumeration to be its own idea.

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