Move the mouse over a page element to reveal hover menus or tooltips. Target elements by snapshot ref, visible text, or CSS selector.
Move the mouse over an element (hover menus).
| Name | Required | Description | Default |
|---|---|---|---|
| ref | No | Element ref from browser_snapshot, e.g. 12 | |
| text | No | Visible text or label of the element, instead of ref | |
| selector | No | CSS selector (first match), instead of ref | |
| snapshot | No | Also return the page snapshot after the action |
Changes observed during successful MCP inspections.
v0.7.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and openWorldHint=true, so the agent knows this is not a pure read. The description adds the hover-menu context but does not explain why the operation is non-read-only (hover can change UI state, reveal menus, trigger tooltips) or what happens if the element is not found.
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 wasted words. It is efficient, though the parenthetical is the only thing preventing it from being a bare restatement of the name.
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?
With no output schema and four optional parameters, the description should at minimum clarify the identifier requirement and mention the snapshot side effect. It covers the core action but leaves the agent to infer the calling contract from the schema.
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%, so all four parameters (ref, text, selector, snapshot) are already documented in the schema. The description adds nothing beyond that, and notably never states that at least one of ref/text/selector must be supplied despite none being required.
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+resource ("Move the mouse over an element") and the parenthetical "(hover menus)" names the typical use case. It is distinguishable from browser_click, but the description never explicitly contrasts itself with that sibling.
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?
"hover menus" implies the when-to-use case (revealing dropdowns/tooltips before clicking), but there is no explicit guidance on when to prefer browser_hover over browser_click, nor any note about needing to hover before interacting with revealed elements.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.