Skip to main content
Glama

interact_and_screenshot

Simulate text input or button clicks on a webpage, including React/Vue controlled fields, then capture the resulting screenshot for visual verification.

Instructions

Simulate user input (with React/Vue controlled component penetration) and/or button click on a webpage, then capture a screenshot.

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": {
      "url": "<url>",
      "outputPath": "<outputPath>"
    },
    "name": "interact_and_screenshot"
  }
}

Input Schema

NameRequiredDescriptionDefault
dprNoDevice scale factor (default: 1)
urlYesTarget webpage URL
delayNoAdditional delay in milliseconds after interactions (default: 1000)
widthNoViewport width in pixels (default: 1920)
heightNoViewport height in pixels (default: 1080)
waitForNoOptional CSS selector to wait for before interactions
selectorNoOptional CSS selector to crop to
inputValueNoText value to type into the input field
outputPathYesPath where the PNG screenshot should be saved
clickSelectorNoCSS selector of an element to click (e.g. submit button, tab, drawer toggle)
inputSelectorNoCSS selector of an input/textarea to inject text into

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv1.0.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations, the description carries the full burden. It does disclose one genuinely useful behavior beyond the schema: React/Vue controlled component penetration, i.e. typed values reach framework state. It omits other significant behavior — headless browser context, failure modes when selectors do not match, ordering of waitFor/delay relative to interactions, and that output is written to disk at outputPath.

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

Conciseness4/5

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

A single front-loaded sentence with no filler, and the interaction-then-capture order is clear. The parenthetical '(with React/Vue controlled component penetration)' is dense but earns its place as non-obvious behavior.

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

Completeness3/5

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

For an 11-parameter browser-automation tool with no annotations and no output schema, the description covers the core flow but leaves gaps: interaction ordering, behavior when optional selectors are absent, and the fact that the result is a file rather than a returned image. The rich schema compensates for parameter detail but not for behavioral context.

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 description coverage is 100%, so all 11 parameters are already documented, establishing a baseline of 3. The description adds only indirect meaning (that inputValue/inputSelector interact via controlled-component penetration) and clarifies no defaults, ordering, or interaction between clickSelector and inputSelector.

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 compound verb chain (simulate user input and/or click) plus a concrete resource (a webpage) and the resulting action (capture a screenshot). This distinguishes it reasonably from take_screenshot (capture only) and inspect_element (inspection), though it never names those siblings explicitly.

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

Usage Guidelines3/5

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

Usage is only implied: the 'and/or ... then capture' phrasing suggests this is the tool for screenshotting after interaction. There is no explicit statement of when to use this instead of take_screenshot, and no exclusions or prerequisites (e.g. 'use when the page requires a click before the target renders').

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