Skip to main content
Glama
Sign In
video-sense

video-sense

by znplusW
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

audio_start

Opens an absolute local audio file as a standalone audio task, with optional start/end seconds, so you can poll status and run ASR transcription when ready.

Instructions

Open an absolute local audio file as an independent audio task. No video task, images or ASR model is created. Supports FFmpeg-readable WAV/MP3/FLAC/M4A/AAC/OGG/Opus and other audio-bearing files. start/end are source seconds; default start=0,end=source duration. Returns id and mediaId immediately, source metadata is probed asynchronously. Poll audio_status until status=ready, then use transcript_start(mode=asr) for optional configured ASR; read transcript_read. ready means source ready, not text complete. Unknown duration requires explicit end. session_stop cancels source/text tasks and retains results.

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": {
      "file": "<file>"
    },
    "name": "audio_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
fileYes
startNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.0

TDQS

A4.6/5.0
Behavior5/5

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

Annotations only declare the generic mutating/non-idempotent/non-destructive profile; the description adds real behavior: returns id and mediaId immediately, probes source metadata asynchronously, and warns that 'ready' means source ready, not text complete. It also states that unknown duration requires an explicit end and that session_stop retains results, which an agent could not infer from structured fields.

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 purpose and scope, then capabilities, then the polling and follow-on call sequence. Dense and largely waste-free, though the telegraphic style ('ready means source ready, not text complete') is terse enough that a reader must parse carefully.

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?

No output schema exists, so the description correctly supplies the return contract (id and mediaId immediately, async metadata) and the full task lifecycle. For a three-parameter async ingestion tool, nothing an agent needs to invoke it and follow up correctly is missing.

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 0% schema description coverage, the description carries the full burden and does well: start/end are source seconds, defaults are start=0 and end=source duration, and unknown-duration files require an explicit end. The file parameter is only qualified as an absolute local path with supported formats, but that is enough to call it correctly.

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 ('Open an absolute local audio file as an independent audio task') and immediately scopes it against siblings by declaring what is NOT created (no video task, images, or ASR model). The contrast with audio_url_start and video_start is clear from 'absolute local audio file'.

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?

Provides a concrete follow-on workflow: poll audio_status until ready, then optionally call transcript_start(mode=asr) and read via transcript_read, with session_stop for cancellation. It does not explicitly say when to prefer audio_url_start for remote sources or video_start for video files, but the scope statement covers most alternative cases.

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

Deploy Server

Other Tools