Skip to main content
Glama

var2_video_look

See the person in a video: where their head is and WHERE THEY LOOK, second by second (camera, up, up-right, left…), plus the free room around them. Call it before placing graphics around a speaker ("put the cards where she is looking"). Prepares the clip once (same preparation var2_video_effect uses, charged like one export, reused afterwards). If it answers preparing, call again with the same arguments (it picks up the same preparation); never loop. Not a generator.

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": {
      "video": "<video>"
    },
    "name": "var2_video_look"
  }
}

Input Schema

NameRequiredDescriptionDefault
videoYesThe clip: a var2 video placeholder_id, a var2 share link or an https URL of a video in var2.
to_secondsNoWhere to stop (default from + 10; at most 60 seconds per call).
aspect_ratioNoThe shape of the clip (default 9:16).
from_secondsNoWhere in the clip to start looking (default 0).
wait_secondsNoHow long to wait for the clip to be prepared (default 40). Leave it at the default: most clients drop a tool call after 60 seconds.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added
  2. Removed
  3. Changed1 schema field changed
    • changedInput schema / properties / wait_seconds / description
      Previous value: -"How long to wait for the clip to be prepared (default 50)."New value: +"How long to wait for the clip to be prepared (default 50). Leave it at the default: most clients drop a tool call after 60 seconds."
  4. Added

TDQS

A4.3/5.0
Behavior5/5

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

Annotations carry only a title, so the description bears the full load and does it well: it discloses that the clip gets prepared once, that preparation is charged like one export, that it is reused afterward, and that a `preparing` response means re-invoke rather than poll in a loop. The cost and idempotent-retry details are exactly the behavioral context an agent cannot get from structured fields.

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?

Front-loads the core capability and the primary use case, then layers cost/async caveats; every sentence carries operational meaning. A few parenthetical asides ('put the cards where she is looking', 'it picks up the same preparation') add flavor but slightly dilute density.

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 5 parameters, a required video input, thin annotations, and no output schema, the description covers purpose, use case, cost model, and the async/retry path that an agent needs to avoid failing the call. It sketches the return content (per-second head and gaze data) but does not fully specify the response shape or units, which is a minor gap given no output schema exists.

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 every parameter (video, from_seconds, to_seconds, aspect_ratio, wait_seconds) is already documented, including defaults and the 60-second-per-call cap. The description adds only the implicit retry rule ('same arguments'), which is correct baseline behavior when the schema does the heavy lifting.

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 and resource ('See the person in a video') plus the exact outputs: head position, gaze direction with enumerated values (camera, up, up-right, left…), and free room per second. It also explicitly distinguishes itself from generator siblings with 'Not a generator,' so an agent can tell what it is and is not without opening the schema.

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 concrete trigger: 'Call it before placing graphics around a speaker' with an example intent ('put the cards where she is looking'), and a clear async protocol: on `preparing`, re-call with the same arguments and never loop. It stops short of naming an alternative sibling (e.g. an endpoint-extraction tool) for cases where gaze is not the goal, so it is clear context rather than a full when/when-not/alternative routing.

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.

Resources