browser_native_dialog

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

With no annotations provided, the description must carry the full behavioral burden. It discloses the platform restriction, permission requirement, and the nature of actions (list, click, type). However, it doesn't disclose potential side effects, failure modes, or whether operations are reversible. For a tool that can click and type in system dialogs, this is a notable gap, though the description does add some useful context beyond the schema.

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 a single, tightly packed paragraph that front-loads the core purpose and then details actions, platform, and permission. Every sentence earns its place, with no fluff or repetition. The structure is efficient and clear.

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 tool with 4 parameters, no output schema, and no annotations, the description covers the essential aspects: what it does, when to use it, what actions are available, and environmental constraints. It doesn't explain return values or error handling, but for a tool that primarily performs side effects, this may be acceptable. The lack of output schema means the agent can't know what to expect, but the description gives enough to invoke it.

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 high (75%), so baseline is 3. The description adds value by explaining the meaning of each action and providing concrete button label examples ('Open', 'Save', 'Don't Save'). It also clarifies the 'text' parameter is for set_text. This goes beyond the schema's sparse field descriptions, enriching the semantics.

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 a specific verb+resource: it inspects or operates native browser dialogs (file picker, print, auth popup, leave page). It explicitly lists the actions ('list', 'click_button', 'set_text') and gives examples. It also distinguishes itself from siblings by noting these are dialogs 'no extension can touch', implying other tools (like browser_dialogs) are for page-level dialogs.

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 gives clear context on when to use this tool: for native dialogs that extensions can't touch. It also specifies platform (macOS only) and permission requirement (Accessibility). It doesn't explicitly name alternative tools for exclusion, but the 'no extension can touch' phrase implies a distinct usage scenario. This is adequate guidance without naming siblings.

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