browser_interactPerform click, type, or scroll actions on page elements using CSS or XPath selectors, so agents can drive real browser interactions during testing and automation.
Click, type into, or scroll an element into view using a CSS or XPath selector.
| Name | Required | Description | Default |
|---|---|---|---|
| text | No | Text to enter. Required only when action is "type". | |
| action | Yes | ||
| selector | Yes | CSS selector or XPath selector such as "xpath=//button". |
Changes observed during successful MCP inspections.
v1.0.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden but discloses almost nothing: it doesn't say whether click waits for element readiness, whether typing appends or replaces text, what errors look like on missing elements, or what is returned. It does clarify that scroll brings an element into view rather than scrolling the page arbitrarily, which is a small useful addition.
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 efficiently sized, though it is under-specified rather than richly informative.
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 side-effecting interaction tool with no annotations and no output schema, the description is too thin: preconditions, failure behavior, and interaction semantics are all missing. Only the selector format and basic action set are conveyed, and mostly via 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 coverage is 67% and the schema already documents the action enum, the text parameter's conditionality, and selector format. The description merely restates the action enum values and never mentions the text parameter, so it adds no meaning beyond the schema.
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 specific verbs (click, type, scroll) and resource (element via CSS/XPath selector), which clearly separates it from navigate/screenshot/inspect siblings. It doesn't explicitly name or contrast with those siblings, so not a 5.
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 guidance on when to use this versus browser_navigate or browser_inspect, and no preconditions such as requiring a page to be loaded first. The only implied usage is that a selector must exist.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.