Skip to main content
Glama

Outil.io

Start video export

start_video_export

Lancer le rendu MP4 d’un snapshot immuable de la version exacte indiquée. Suivre get_video_export jusqu’à done ; un seul export actif par workspace.

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": {
      "projectId": "<projectId>",
      "version": "<version>"
    },
    "name": "start_video_export"
  }
}

Input Schema

NameRequiredDescriptionDefault
versionYes
projectIdYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Added

TDQS

A3.8/5.0
Behavior3/5

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

Annotations already declare a non-read-only, non-destructive, closed-world write, and the description adds genuinely new behavior: the render is async (poll get_video_export) and only one export may be active per workspace. It stops short of saying what the call returns (an export id needed for polling), whether re-invoking is idempotent, or how the concurrency conflict surfaces as an error.

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 sentences, zero filler: the action and its snapshot semantics come first, then the polling instruction and the concurrency limit. Every clause carries operational 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, two required params, and an asynchronous job model, the description covers the essentials: what is rendered, from which version, how to track progress, and the one-active-export limit. The remaining gap is the return value / handle needed to call get_video_export and the failure mode on conflict.

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 0%, so the description carries the burden: it clarifies that 'version' must be the exact version whose immutable snapshot is rendered, and that scoping is per workspace. It never mentions projectId or its uuid format, and does not explain what 'version' being an integer index means, leaving one of two required parameters undocumented anywhere.

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?

The description names a specific verb and artifact ('Lancer le rendu MP4') and pins the scope to 'un snapshot immuable de la version exacte indiquée', which clearly separates it from the many other export_* and video-* siblings. It falls short of 5 only because the naming is generic enough ('export') that an agent must still read the second clause to know it is asynchronous rather than a direct download.

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?

It gives an explicit follow-up workflow ('Suivre get_video_export jusqu'à done') and a hard precondition ('un seul export actif par workspace'), which tells the agent both what to do next and what will block the call. It does not state what to do if an export is already active, nor when to prefer list_video_exports or cancel paths instead.

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.