browser_cdpSend any Chrome DevTools Protocol command to the current browser tab and get the raw response, enabling direct low-level control of live pages.
Send an arbitrary Chrome DevTools Protocol command to the current tab and return the raw response. Use with care.
| Name | Required | Description | Default |
|---|---|---|---|
| method | Yes | The Chrome DevTools Protocol method, e.g. "Page.captureScreenshot" | |
| params | No | Parameters for the CDP method |
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, and it discloses only that the target is the current tab and the return is raw. It does not say that arbitrary CDP commands can mutate or destroy page state, whether the call blocks or times out, or how errors surface.
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?
Two short sentences, front-loaded with the action and target, with no wasted words. The trailing 'Use with care' is terse but carries little information.
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 an open-ended passthrough tool with a free-form params object and no output schema, the description covers scope (current tab) and return shape (raw response) but omits risk profile, failure behavior, and any hint about the domain of valid CDP methods.
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% and both parameters (method, params) are already documented in the schema with an example. The description adds nothing beyond 'arbitrary command', so the baseline 3 applies.
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 ('Send') and resource ('an arbitrary Chrome DevTools Protocol command to the current tab') plus the response shape ('raw response'). It is clearly distinct in kind from the high-level siblings, though it never names the escape-hatch relationship explicitly.
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?
'Use with care' is a vague caution, not guidance. There is no statement of when to prefer this over browser_evaluate, browser_screenshot, browser_click, or other task-specific siblings, nor any prerequisites for calling it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.