action_menu

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

With no annotations, the description carries the behavioral disclosure burden. It does reveal an important side effect: a confirmation dialog may open and is reported as changes.dialog_opened, with instructions on how to proceed. However, it does not disclose potential destructive/irreversible consequences (e.g., 'Delete') or any prerequisites such as the menu needing to be open/visible.

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 purpose is front-loaded and the dialog-handling instruction is actionable. Both sentences earn their place, though the second sentence is dense with multiple connected clauses. No filler, but not as crisp as it could be.

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 UI-action tool with no annotations and no schema descriptions, the description covers the primary flow and dialog follow-up well. However, the `scope` parameter semantics and behavior when no matching label exists are missing. Since an output schema exists, not restating return values is acceptable, but the scope gap remains significant.

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 explains the required `item` parameter as a dropdown label with examples, but the optional `scope` parameter is never mentioned. Since schema description coverage is 0%, the description is the only documentation source, and it leaves `scope` completely unexplained.

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 states the specific action ('Pick an entry ... by label'), the exact UI surface ('cog / "Actions" dropdown of the current view'), and provides concrete label examples. This clearly distinguishes it from sibling tools like open_menu or click_button.

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?

It defines the situational context (current view's Actions menu) and explains the follow-up behavior when a confirmation dialog appears, directing the agent to confirm with click_button or cancel with click_button('discard'). It does not explicitly contrast with alternatives or state exclusions, so it stops short of a full when/when-not guide.

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