Skip to main content
Glama
Galbaz1

video-research-mcp

by Galbaz1
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

Video Create Session

video_create_session

Create a persistent session for multi-turn video exploration from a YouTube URL or local file, enabling context-cached follow-up questions.

Instructions

Create a persistent session for multi-turn video exploration.

Provide exactly one of url or file_path. When download=True and the source is YouTube, the video is downloaded via yt-dlp, uploaded to the Gemini File API, and context-cached for fast multi-turn use.

Input Schema

NameRequiredDescriptionDefault
urlNoYouTube video URL.
scopeNoExact workspace/notebook isolation for sessions and derived memory; omit for legacy unscoped sessions
downloadNoDownload YouTube video locally for cached multi-turn sessions. Slower startup (~2 min) but faster and cheaper per turn. Requires yt-dlp installed.
file_pathNoPath to a local video file.
descriptionNoSession purpose or focus area

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changedv0.7.1
    • addedInput schema / properties / scope
      Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": {
+        "type": "string"
+      },
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ],
+  "default": null,
+  "description": "Exact workspace/notebook isolation for sessions and derived memory; omit for legacy unscoped sessions"
+}
  2. Changed2 schema fields changedv0.6.1
    • addedInput schema / properties / file_path / description
      Added value: +"Path to a local video file."
    • addedInput schema / properties / url / description
      Added value: +"YouTube video URL."
  3. First observedv0.6.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare this is a state-creating (readOnlyHint=false, idempotentHint=false) but non-destructive open-world operation. The description goes beyond them by disclosing the concrete side effect chain for download=True: yt-dlp fetch, upload to the Gemini File API, and context-caching, which tells the agent what actually happens on disk/network. Session lifetime and continuation behavior are left unstated.

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?

Two sentences, front-loaded with purpose followed by the key constraint and the download caveat. No filler; each clause carries information, though the download sentence is dense.

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?

An output schema exists so return values need no explanation, and all five parameters are schema-documented. The description supplies the exclusivity rule and the download side-effect, making it sufficiently complete for a session-creation tool; only agent-facing routing and session lifecycle are absent.

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

Parameters4/5

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

Schema description coverage is 100%, so the baseline is 3, and the description adds meaning beyond the schema by stating the mutual-exclusivity rule for url/file_path that the schema does not encode. It does not clarify the scope parameter's semantics, which the schema already covers.

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 verb and resource (create a persistent session for multi-turn video exploration), which distinguishes it from one-shot tools like video_analyze. However, it does not name the natural sibling video_continue_session or otherwise explicitly route the agent among the many video_* tools.

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?

It gives a hard correctness constraint ('Provide exactly one of url or file_path') that is genuinely useful usage guidance. But it never states when to prefer this tool over alternatives such as video_analyze or video_continue_session, so the when-to-use dimension is only implied.

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

Deploy Server

Other Tools