Skip to main content
Glama

manage_reel

Create a highlights reel from one or many videos, then edit individual moments (longer, shorter, earlier, later) and rebuild without re-detecting. Pool multiple videos to rank the best moments across all.

Instructions

Create and iterate on a highlights reel. Detection runs once with action 'new'; after that, edit individual moments fast (longer/shorter/earlier/later/shift/drop/toggle) and rebuild without re-detecting. Pass video_paths (a list) to pool many videos and rank the best moments across all of them. Actions: 'new' (video_path or video_paths, profile, format, top_n, min_dur, max_dur), 'list', 'show' (session_id), 'edit' (session_id, index, op, seconds), 'build' (session_id), 'delete' (session_id).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
opNoFor 'edit': how to change the moment
endNoFor 'edit' with op 'set': absolute end time in seconds
autoNoFor 'new': let detection pick the best moments and how many, ignoring top_n/min_dur/max_dur
logoNoFor 'new'/'build': path to a logo image overlaid top-right on the reel; empty string removes it
indexNoFor 'edit': 1-based moment number to adjust
startNoFor 'edit' with op 'set': absolute start time in seconds
top_nNoFor 'new': number of moments
actionYesWhat to do with the reel
formatNoFor 'new': reel aspect ratio (default horizontal)
max_durNoFor 'new': longest moment in seconds (default 60)
min_durNoFor 'new': shortest moment in seconds (default 15)
profileNoFor 'new': detection profile (default auto)
secondsNoFor 'edit': seconds for longer/shorter/earlier/later/shift
session_idNoFor show/edit/build/delete: the reel session id returned by 'new'
video_pathNoFor 'new': path to the source video
video_pathsNoFor 'new': many source videos to pool and rank the best moments across all of them
Behavior4/5

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

With no annotations, the description discloses key behaviors: detection runs once, editing does not re-detect, and video_paths pools videos to rank moments. It does not cover auth or rate limits but provides substantial behavioral context.

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?

The description is concise yet informative, front-loading the overall purpose and then enumerating actions. It is slightly dense but avoids redundancy, earning its content.

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

Completeness3/5

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

The description covers all actions and parameter usage well, but lacks details on return values (e.g., what 'new' returns) and does not address output behavior, leaving some gaps for a complex tool with 16 parameters.

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 coverage is 100%, and the description adds significant context beyond parameter names, such as how video_paths pools multiple videos and the workflow for actions, adding value beyond the schema.

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?

The description clearly states the tool creates and iterates on a highlights reel, specifying its unique workflow (detection once, then iterative editing) and distinguishing it from sibling tools like create_clip (which handles individual clips).

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?

The description outlines a clear workflow and lists all actions, but does not explicitly state when to use this tool over siblings like batch_create_clips or suggest alternatives for specific tasks.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/nmbrthirteen/podcli'

If you have feedback or need assistance with the MCP directory API, please join our Discord server