Skip to main content
Glama

Clip a file on this computer

queue_local_file

Process an existing local video file through Clips Kitty's clip pipeline to generate captioned 9:16 clips without uploading it.

Instructions

Same pipeline for a video already on disk. Nothing is uploaded. Set channel when you know it: creator learning keys off it.

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": {
      "path": "<path>"
    },
    "name": "queue_local_file"
  }
}

Input Schema

NameRequiredDescriptionDefault
pathYesFull path to the video file
focusNoWhat the person wants the clips to be about or to include, in their own words: a topic they talk about, a moment that happened, a time range ("1:35-1:55", "near the end"), or a style (funny moments, laughing, hype, reactions). Pass their sentence as written, keeping words like "make sure" and "at least two": those make it a must-have. It adds weight to those moments and never removes others, so "avoid X" is not something it can do.
forceNoProcess this file again for an intentional comparison.
sportNoThe video is a match or a game: its moments (soccer: goals, saves, cards; basketball: dunks, threes, blocks, game winners, and the crowd, bench and courtside reactions) are found from the crowd, the commentary and the scoreboard, one clip per moment with its build-up and reaction, framed to follow the play. Not with gaming or podcast.
titleNoDefaults to the filename
gamingNoA game stream: the streamer's webcam in one half and the game in the other, or the game filling the screen when there is no webcam. The streamer is whoever speaks in sync with the audio, never the biggest face. Not with vertical_live, podcast or longform.
channelNoWhose channel this is
captionsNoBurn captions into the clips.
pipelineNoAn installed, enabled SDK pipeline. For a Gaming detector also set gaming=true. Use its actual id, never guess.
max_clipsNoCap clips from this video
min_scoreNoQuality bar, 0-100
source_urlNoWhere the video was originally streamed, if known (never guess)
gaming_layoutNoThe existing Gaming layout and webcam/game boxes, validated by the engine. Omit to use Gaming's automatic layout detector. Set only from the user's chosen layout.
vertical_liveNoThe video is a livestream that was already vertical (9:16) when streamed: keep its own layout, no face tracking or reframing. Refused if the video is not 9:16. Not with podcast or longform.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.3/5.0
Behavior3/5

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

With no annotations, the description carries the full disclosure burden. It usefully states that nothing is uploaded (local processing) and that the channel feeds creator learning, but it omits that this enqueues an asynchronous job, what is returned, and what re-processing or force does at a behavioral level.

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?

Three short sentences, front-loaded with the key operational fact (local file, nothing uploaded) and no filler. The only weakness is that the leading "Same pipeline" is referential and costs the reader a moment of ambiguity.

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

Completeness2/5

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

For a 14-parameter tool with nested objects, zero annotations, and no output schema, this is thin. An agent is not told it is starting an async job, how to track it (queue_status / job_status), or how the mode parameters interact, which is the information this definition should have supplied.

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 coverage is 100%, so the baseline is 3. The description adds real meaning for exactly one field (channel drives creator learning), but says nothing about path, pipeline, force, or the large sport/gaming mode branches that dominate the 14-parameter surface.

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?

"Same pipeline for a video already on disk" plus "Nothing is uploaded" makes clear this clips a local file rather than an ingested URL, a meaningful distinction. However, it never names the sibling it is the local counterpart of (queue_video), so the differentiation rests on the agent inferring what "same pipeline" refers to.

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?

Usage is only implied: use this when the video is already on disk. There is no explicit when-to-use versus queue_video, no prerequisite or failure guidance, and the only directive ("Set channel when you know it") targets one parameter rather than the tool choice.

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