Skip to main content
Glama

Outil.io

Record website video

record_website_video
Destructive

Filmer un site public dans Chromium (1080p, mobile ou ordinateur) avec curseur visible, onde de clic, défilement fluide, survols, saisie de texte. Crée un média du projet et renvoie focusPoints (temps source + position) pour add_video_focus_zoom. 90 s maximum.

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>"
    },
    "name": "record_website_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
hdNo
urlYes
nameNo
stepsNo
aspectNo
cursorNo
deviceNodesktop
maxSecondsNo
minSecondsNo
dismissCookiesNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.9/5.0
Behavior4/5

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

Annotations already flag a mutating, open-world, destructive operation; the description adds valuable context beyond them by stating it creates a project media, limits to public sites (no auth implied), caps capture at 90 seconds, and runs in Chromium at 1080p. It still omits failure modes, how long the recording takes, and whether existing media is overwritten.

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?

Three dense sentences that front-load the core action and fold the visual-feature detail into a parenthetical list, with the output contract and the time cap at the end. No filler, though the feature list is compressed enough that some parameter meaning is lost.

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 a 10-parameter mutating recorder with a nested steps array and no output schema, the description does cover what the tool produces (focusPoints) and the hard 90-second boundary. It leaves out step-sequence semantics, the min/max duration interaction, aspect/device interplay and cookie dismissal, which an agent would need to invoke it well.

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

Parameters2/5

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

Schema coverage is 0% across 10 parameters, so the description carries the full burden and mostly does not: 'steps' (the nested action array: goto/wait/scroll/click/hover/type/press/move) is only hinted at through prose about cursor, hover and typing, and hd, name, aspect, minSeconds/maxSeconds and dismissCookies are never explained. 'mobile ou ordinateur' and 'curseur visible' partially map to device and cursor, and '90 s maximum' hints at maxSeconds, but the bulk of parameter meaning is undocumented.

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?

Precise verb and resource ('Filmer un site public dans Chromium'), plus concrete production detail (1080p, mobile/desktop, cursor, click ripple, scroll, hover, typing). It also names the downstream consumer add_video_focus_zoom, so the agent can tell it apart from record_website_inventory and clone_website siblings.

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?

States the operative constraint (90 s max) and clearly frames the output as focusPoints feeding add_video_focus_zoom, which implicitly defines the workflow slot. It does not explicitly exclude alternatives such as record_website_inventory or clone_website, so it falls short of a full when/when-not statement.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.