Resizes the controlled browser window within 320–3840 by 200–2160 pixels and returns its actual rectangle; does not change zoom and invalidates existing references.
Resize the controlled window to 320-3840 by 200-2160 pixels and return its actual rectangle. Does not change zoom; invalidates references.
| Name | Required | Description | Default |
|---|---|---|---|
| width | Yes | ||
| height | Yes |
Changes observed during successful MCP inspections.
v0.3.0Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations at all, the description carries the full burden and does useful work: it discloses that the returned value is the actual rectangle (implying the request may not be honored exactly), that zoom is unaffected, and that element references are invalidated — a real side effect an agent must plan around. It stops short of naming prerequisites (session must exist) or what happens on out-of-range input.
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, zero filler, with the core action and bounds front-loaded and the caveats (zoom, reference invalidation) trailing.
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 low-complexity two-parameter tool with no output schema, the description covers action, bounds, side effects, and the shape of the return value. The remaining gap is prerequisite/session state and out-of-range handling, which is minor but non-zero given no annotations exist to fill it.
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, and it does partially by giving the accepted range in pixels for both dimensions (320-3840 width, 200-2160 height). However it does not say whether out-of-range values are clamped or rejected, nor whether the actual rectangle can differ due to OS/window chrome constraints.
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 and resource ("Resize the controlled window") with concrete bounds, and no sibling in the list offers resize semantics, so it is unambiguously distinguishable from browser_windows, browser_switch_window, and browser_start.
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?
Usage is only implied — an agent can infer this is for setting the viewport before layout-sensitive work — but there is no explicit when-to-use, no prerequisite (e.g. an active browser session), and no statement of when resizing is unnecessary or harmful.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.