Skip to main content
Glama

resize_window

Set a tab's viewport to specific width and height CSS pixels to test phone or responsive layouts without resizing the browser window.

Instructions

Set a tab's viewport to width x height CSS pixels (200 to 4000 each), e.g. to check a phone layout.

Only the page inside that tab changes size; Zen's window stays as it is. The size stays through
reloads and navigations in the tab, even after zenpilot disconnects, until you call resize_window
without width and height. Do that when you're done.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "resize_window"
  }
}

Input Schema

NameRequiredDescriptionDefault
widthNo
heightNo
tab_idNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.7.0

TDQS

A4.3/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations present, the description carries the full burden and does so well: it discloses the persistence model (survives reloads, navigations, and disconnect), the blast radius (page viewport only, not the Zen window), the valid range (200–4000 px), and the reset mechanism. These are exactly the non-obvious traits an agent needs before calling a stateful mutation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Two short paragraphs, front-loaded with the action and its range, followed by persistence and cleanup. Every sentence carries information an agent would otherwise have to discover empirically; no wasted clauses.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a stateful tool with no annotations, no output schema, and three undocumented parameters, the description covers scope, lifetime, and cleanup thoroughly. Remaining gaps are tab_id semantics, out-of-range error behavior, and what the call returns, none of which are severe but all of which an agent may hit.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0% and the parameters have only bare titles, so the description must compensate. It does for width and height (CSS pixels, 200–4000 bounds, and the special omitted-both reset semantics), but tab_id is never mentioned — an agent must guess whether it targets the active tab, what the default is, or how it relates to switch_tab.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb and resource ('Set a tab's viewport to width x height CSS pixels') plus a concrete example use ('check a phone layout'), and clarifies scope ('Only the page inside that tab changes size; Zen's window stays as it is'). It does not explicitly differentiate itself from any sibling, but the action is unambiguous enough that confusion is unlikely.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives a clear use context ('to check a phone layout') and an explicit cleanup instruction: call resize_window without width and height when done. No alternatives or when-not-to-use conditions are named, but no sibling tool covers viewport resizing, so the guidance is effectively complete for the available options.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.