Skip to main content
Glama
Sign In
video-sense

video-sense

by znplusW
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Local

audio_url_start

Open a public audio URL or supported media page to asynchronously probe and stream bounded audio blocks for ASR transcription without waiting for a full download; poll status for readiness.

Instructions

Open a public HTTP(S) audio direct link or resolver-supported media/audio page, independently of video tasks. Resolves/probes asynchronously and streams audio into bounded ASR blocks when requested; does not wait for a complete media download. sourceType=auto recognizes common audio/HLS/DASH extensions, direct forces extensionless media, page forces yt-dlp. Page resolution prefers audio-only streams with an audio-bearing fallback; itemIndex 1..100 selects ONE page/playlist item, default1. start/end are source seconds; unknown duration needs explicit end. No images or automatic ASR. Poll audio_status for ready/mediaId; then transcript_start(mode=subtitles/asr), read transcript_read. No cookies/DRM/live input. Availability/seeking/traffic depend on the source. Each network phase is limited to 1GiB; source probing is bounded, ASR tasks max1800 source seconds. session_stop cancels.

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": {
      "url": "<url>"
    },
    "name": "audio_url_start"
  }
}

Input Schema

NameRequiredDescriptionDefault
endNo
urlYes
startNo
itemIndexNo
sourceTypeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.9.0

TDQS

A4.4/5.0
Behavior4/5

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

Annotations only declare readOnly=false, openWorld=true, idempotent=false, destructive=false; the description adds substantial behavior beyond that: asynchronous resolution, non-blocking streaming, per-phase 1GiB network limits, bounded probing, a 1800 source-second ASR cap, no cookie/DRM/live support, and that availability/seeking/traffic depend on the source. The one shortfall is that it never says what the immediate return payload is or how failures surface, so an agent still has to infer the error path.

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 packed with load-bearing detail; nearly every clause adds a constraint or a routing hint. It is dense and semicolon-chained with abbreviations (ASR, 1GiB, yt-dlp), which makes it harder to scan than a bulleted form, but no sentence is filler.

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

Completeness4/5

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

For a complex async, open-world tool with no output schema, the description covers input modes, limits, exclusions, the follow-up polling path, and where mediaId comes from (audio_status). What is left implicit is the immediate call result (job handle vs error), which an agent must discover empirically.

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 carries the full burden and does: sourceType auto/direct/page semantics with the extensionless-media and yt-dlp cases, itemIndex range plus 'selects ONE item' and default 1, start/end as source seconds with the rule that unknown duration requires explicit end. These are meanings the schema's bare types and enums cannot convey.

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 opening sentence names a concrete verb and resource: opening a public HTTP(S) audio direct link or resolver-supported media/audio page, and explicitly scopes it as independent of video tasks. That single clause distinguishes it from video_url_start/video_start and tells an agent what object it operates on without opening the schema.

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?

Usage context is stated (async resolve/probe, bounded ASR streaming, no wait for full download) plus explicit exclusions: no images, no automatic ASR, no cookies/DRM/live input. It also routes the agent through a follow-up workflow (poll audio_status, then transcript_start, then transcript_read) and names session_stop for cancellation. The one gap is that it never contrasts itself with the sibling audio_start (local vs URL source), so the alternative-selection rule is only implied.

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