Skip to main content
Glama

Kubeez

trim_video

Scope: generate:media. Cut a window out of any publicly accessible video URL and host the trimmed clip — no manual upload required. The server downloads the source, runs ffmpeg -c copy (lossless stream-copy, no re-encode), uploads the trimmed MP4, and returns a public url you can pass straight into generate_media as a source_media_urls value. ARGS: source_url (required — public video URL); start_s (default 0); end_s (required — must be > start_s; range capped at 60s). USE WHEN: a model needs a short reference clip (Gemini Omni Video expects ≤10s; Kling Motion Control caps at 30s) and the user's source is longer than the cap. WHICH WINDOW IS THE USER'S CALL: when the source exceeds the cap, ASK the user which segment to keep (in the Kubeez chat UI, emit the trim_request block instead) and only then trim. Never silently pick a window yourself — agents defaulting to the opening seconds of a long clip discard the moment the user actually wanted. Auto-trim ONLY when the user already named the moment ('use the part at 1:20') or explicitly told you to choose. RETURNS: { url, size_bytes, duration_s, start_s, end_s, elapsed_s }. ERRORS: invalid_trim_range, missing_source_url, source_too_large (provider cap, currently 500 MB), trim_too_long (>60s output), source_fetch_failed (source URL 4xx / unreachable), ffmpeg_failed, processor_timeout, processor_unavailable.

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": {
      "source_url": "<source_url>",
      "end_s": "<end_s>"
    },
    "name": "trim_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
end_sYes
start_sNo
source_urlYes

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.7/5.0
Behavior4/5

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

Annotations already declare readOnlyHint=false, openWorldHint=true and destructiveHint=false, so the description's job is to add operational context — and it does: server-side download, lossless ffmpeg -c copy with no re-encode, hosting of the output, a 500 MB source cap and a 60s output cap. The enumerated error strings (source_fetch_failed, trim_too_long, processor_timeout, etc.) further tell the agent how failure will surface. It could still say whether hosted clips persist or are billed, which keeps it from 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?

Front-loaded with a Scope line and organized under labeled sections (ARGS, USE WHEN, RETURNS, ERRORS), which makes it easy to scan. It is dense and the user-intent paragraph restates its point a couple of ways ('ASK the user' / 'Never silently pick a window yourself' / 'Auto-trim ONLY when...'), which is deliberate emphasis but costs length.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a three-parameter mutation tool with an output schema, the definition covers the operation, the constraints, the user-confirmation policy, the return shape and every named failure mode. Nothing an agent needs in order to call this correctly is missing.

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

Parameters5/5

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

Schema description coverage is 0%, so the description must carry the parameter burden and does so for all three: source_url as a required public URL, start_s defaulting to 0, and end_s required with the relational constraint end_s > start_s plus a 60s range cap that the schema's exclusiveMinimum alone does not convey. The subtype semantics (window, seconds, ordering) exceed what the raw schema expresses.

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 — 'Cut a window out of any publicly accessible video URL and host the trimmed clip' — and scopes itself to generate:media, differentiating it from siblings like generate_media or estimate. The downstream handoff ('returns a public url you can pass straight into generate_media as a source_media_urls value') makes the tool's role unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Explicit USE WHEN block names the triggering condition (a model needs a short reference clip and the source exceeds the model's cap, citing Gemini Omni Video ≤10s and Kling Motion Control ≤30s). It goes further with a when-not clause: never silently pick a window, ask the user first, with explicit exceptions for when the user named the moment or delegated the choice.

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