Run browser test steps by clicking, filling, pressing, scrolling, and waiting using element references or selectors, while saving screenshots and errors for debugging.
Run browser test steps and save screenshots/errors. click/fill steps accept ref (from browser_observe), selector, or text/placeholder. For repeated flows prefer browser_flow_record/browser_flow_run.
| Name | Required | Description | Default |
|---|---|---|---|
| steps | Yes |
Changes observed during successful MCP inspections.
v1.0.1Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden of behavioral disclosure. It mentions saving screenshots/errors, but does not disclose critical behaviors such as whether execution stops on the first error, whether a browser must already be open, how results are returned, or what happens on failure. This is a significant gap for a multi-step automation tool.
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 concise and front-loaded with the primary purpose, followed by a key usage detail and an alternative. Two sentences with no fluff or redundancy, achieving efficiency.
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?
Given the complexity of the steps array with multiple actions and properties, and no output schema or annotations, the description is far too brief. It lacks explanations of each action, error handling, prerequisites, and return format, making it inadequate for reliable invocation.
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 0%, so the description must compensate. It adds semantics for click/fill steps (ref/selector/placeholder) but leaves the other actions (open, press, scroll, wait, screenshot) and properties (url, name, value) unexplained. An agent cannot correctly construct all step types from this description alone.
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 the tool runs browser test steps and saves screenshots/errors, giving a specific verb and resource. It also hints at differentiation by mentioning that click/fill steps accept ref/selector/placeholder, and points to flow tools for repeated flows, distinguishing from some siblings.
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 provides an explicit alternative for repeated flows ('For repeated flows prefer browser_flow_record/browser_flow_run'), which is a clear when-not scenario. However, it does not explicitly state when to use this tool versus the individual browser_click/browser_fill tools, leaving some ambiguity about the intended use case.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.