Skip to main content
Glama

Join up to 3 clips into one video

stitch_videos
Idempotent

Joins 1–3 clips into one video to post, in order. Each clip is a ready 'own' upload (source_id) or one of your ready videos (video_id), cut to start/end seconds (each at least 0.5 s, 10 minutes in all); overlap: seconds of crossfade into the previous clip (0–2). request_id: a new unique string per video; the same request_id returns the same video, never a second one. Poll get_video until ready.

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": {
      "request_id": "<request_id>",
      "clips": "<clips>"
    },
    "name": "stitch_videos"
  }
}

Input Schema

NameRequiredDescriptionDefault
clipsYes
request_idYesA new unique id per stitched video; repeat it only to retry the same request

Output Schema

NameRequiredDescriptionDefault
statusYes
video_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, idempotentHint=true and destructiveHint=false; the description goes beyond them by spelling out the idempotency contract concretely ("the same request_id returns the same video, never a second one") and the asynchronous completion pattern (poll get_video). It does not mention cost, permissions, failure modes, or what happens to the input clips, which keeps it off a 5.

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?

Everything is packed into a few dense sentences that front-load the action and ordering, then the clip validity rules, then idempotency and polling. The telegraphic style ("to post", "10 minutes in all") costs a bit of readability, but no sentence is wasted.

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?

For a mutation tool with an output schema, the description covers the essentials an agent needs: valid clip sources, per-clip limits, idempotency keys, and the polling follow-up. Missing only edge-case behavior (what happens on invalid/expired source clips) which is not strictly required to call it correctly.

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?

With 50% schema coverage, the description compensates by adding constraints absent from the schema: each cut is at least 0.5 s, total length is capped at 10 minutes, and overlap is a 0–2 s crossfade into the previous clip. It also clarifies request_id uniqueness semantics beyond the schema's pattern description. The start/end pairing is described but not fully specified (e.g. whether end must exceed start).

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?

"Joins 1–3 clips into one video to post, in order" names the specific verb (joins), the resource (clips), the hard limit (1–3) and the ordering guarantee. An agent can distinguish this from the sibling upload/video tools without inspecting any 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?

It states the prerequisite that makes a call valid — each clip must be a *ready* 'own' upload (source_id) or a *ready* video (video_id) — and gives the follow-up step "Poll get_video until ready." It stops short of explicit when-not guidance or pointing at the alternative workflow (e.g. creating the source via use_own_video/create_upload first), so it's clear context without exclusions.

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.