Skip to main content
Glama

Scroll

browser_scroll

Scroll the current page by about one screen in a chosen direction and return the newly visible view with element references.

Instructions

Scroll the page about one screen; returns the screen now in view, with refs. To reach a named element, browser_find; for text, browser_get_text.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "direction": "<direction>"
    },
    "name": "browser_scroll"
  }
}

Input Schema

NameRequiredDescriptionDefault
directionYesdown: the next screen; up: back

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.1.1
    • addedInput schema / properties / direction / description
      Added value: +"down: the next screen; up: back"
  2. First observed

TDQS

A4.2/5.0
Behavior3/5

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

The annotations already declare openWorldHint=true, destructiveHint=false and readOnlyHint=false, so the safety profile is covered structurally. The description's real addition is that the call returns the newly visible screen with refs, which matters for chaining further actions. However, it says nothing about page-load waiting, what happens at the document edge, or whether previously captured refs remain valid after scrolling — meaningful omissions for a viewport-mutating tool.

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 tight sentences with no filler: capability and return value first, then routing to the correct sibling. Every clause carries operative information.

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?

With no output schema, the description correctly compensates by describing the return value (visible screen plus refs), and the single required parameter is fully covered by the schema. It falls short only on edge behavior — end-of-page, loading waits, and ref staleness — which an agent driving a browser may need.

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

Parameters3/5

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

Schema coverage is 100% and the enum already documents down as 'the next screen' and up as 'back', so the baseline of 3 applies. The phrase 'about one screen' adds a little granularity for the vertical directions but says nothing about the horizontal left/right cases or whether any overshoot occurs.

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

Purpose5/5

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

States a specific verb (scroll), the resource (the page), and the exact magnitude (about one screen), then describes the return ('the screen now in view, with refs'). An agent can immediately distinguish this from browser_snapshot or browser_query without opening any schema.

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

Usage Guidelines5/5

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

Explicitly names the alternative tools and the condition that selects each: browser_find for reaching a named element, browser_get_text for text. This is a clear when-not-to-use rule alongside the implicit when-to-use (move the viewport).

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