Skip to main content
Glama

convert_video

Convert video files between formats, with optional trimming, resizing, bitrate adjustments, subtitle burn-in, and frame extraction.

Instructions

Convert video files. Input: mp4, webm, avi, mov, mkv, flv, wmv, m4v, 3gp, ts, m2ts, vob, ogv, hevc/h265. Output: mp4, webm, avi, mov, mkv, gif, ts, ogv, flv, hevc. Supports: trim, resize, fps, bitrate, CRF, preset, hardware acceleration, subtitle burn-in, frame extraction.

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": {
      "inputPath": "<inputPath>",
      "outputPath": "<outputPath>"
    },
    "name": "convert_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
crfNoConstant Rate Factor 0-51 (optional, lower=better quality)
fpsNoFrames per second (optional)
presetNoEncoding preset: ultrafast, fast, medium, slow (optional)
hwAccelNoEnable hardware acceleration (optional)
noAudioNoStrip audio (optional)
durationNoTrim duration e.g. '00:02:00' (optional)
frameRateNoFrames per second to extract (optional, default 1)
inputPathYesAbsolute path to input video file
startTimeNoTrim start e.g. '00:01:30' (optional)
audioCodecNoForce audio codec e.g. aac, libopus (optional)
outputPathYesAbsolute path for output file (include extension)
resolutionNoOutput resolution e.g. '1920x1080' (optional)
videoCodecNoForce video codec e.g. libx264, libx265, libvpx-vp9 (optional)
audioBitrateNoAudio bitrate e.g. '128k' (optional)
subtitlePathNoPath to .srt or .ass subtitle file to burn in (optional)
videoBitrateNoVideo bitrate e.g. '2000k' (optional)
extractFramesNoExtract frames as images (optional)

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv2.1.0

TDQS

B3.2/5.0
Behavior2/5

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

No annotations are provided, so the description carries the full burden, and it discloses almost nothing behavioral: no mention of whether outputPath is overwritten, what happens on unsupported formats, whether the call blocks for long encodes, or what is returned. The feature list (trim, resize, subtitle burn-in, hw accel) describes capability rather than behavior, and those same fields are already visible in the schema.

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 the purpose, then formats, then capabilities. The long enumerations of codecs and containers are dense but arguably the most useful signal; overall there is little wasted wording.

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?

For a 17-parameter tool with no annotations and no output schema, the description should clarify at least the output contract for mode-switching parameters like extractFrames (frames vs. a single video at outputPath) and overwrite behavior. It is adequate but leaves real ambiguity an agent would hit on the first call.

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 description coverage is 100%, so the schema already defines all 17 parameters with examples such as CRF ranges and time format. The description adds only a high-level capability summary and does not clarify ambiguous interactions, notably where extracted frames are written when extractFrames is used.

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?

The description opens with a specific verb+resource ('Convert video files') and then enumerates the exact input and output container formats, which cleanly separates it from siblings like convert_audio, convert_image, and convert_document. It stops short of naming a sibling it is not, so it lands at 4 rather than 5.

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 by the format lists; there is no explicit statement of when to choose this tool over convert_audio (e.g. to strip audio) or batch_convert (multiple files). The capability list hints at what operations are possible, but no exclusions or alternative-selection rules are given.

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