Skip to main content
Glama
Sign In

FilmLab

by com.thefilmradar
OverviewDiscussionsAdmin

Spoken Words

lab_wortzeiten
Read-only

Every spoken word with its start and end time, for a clip (video_id), an audio track (audio_id) or an uploaded file (project_id + asset_key). Use it to cut pauses without cutting into a word, to time captions, or to land a graphic on an exact word — instead of guessing seconds from the waveform. Up to 20 min of sound per source; the first call transcribes (Fish Audio, about 0.36 USD per audio hour, booked to the operator, not your credits), every later call for the same sound is served from the cache for free. Returns at most 300 s of words per page; continue with weiter_von_s. Speech recognition spells names the way they sound — check names before you put them on screen.

Input Schema

NameRequiredDescriptionDefault
bis_sNoEnd of the page; at most 300 s after von_s
von_sNoStart of the page in seconds (default 0)
spracheNoSpoken language (default de) — the same list the backend accepts
audio_idNoAudio track id (from lab_list_audio)
video_idNoGenerated video id — its own soundtrack. Give exactly one of video_id, audio_id, asset_key
asset_keyNoStorage key of an uploaded sound or video file (from lab_add_media). Needs project_id
project_idNoProject the asset_key belongs to — required with asset_key
nur_eigene_datenNoOnly for a model that sends inputs to China or a US recipient without a documented basis, when the step carries images, clips, voices or faces. Means: this material shows or contains no real person other than the human using this account. Set it ONLY after the human has said exactly that for THIS step; never assume it, never reuse it for the next step. Not needed when the human has declared this material in the FilmLab app: the backend reads that declaration, also for material derived from it; only the app can store one. An LK reference, a licensed likeness or another person's agreement does not replace it. Without it the backend refuses with drittland_dritte_gesperrt before any charge; then use a non-gated model or text only.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / nur_eigene_daten / description
      Previous value: -"Only for a model that sends inputs to China or a US recipient without a documented basis, when the step carries images, clips, voices or faces. Means: this material shows or contains no real person other than the human using this account. Set it ONLY after the human has said exactly that for THIS step; never assume it, never reuse it for the next step. An LK reference, a licensed likeness or another person's agreement does not replace it. Without it the backend refuses with drittland_dritte_gesperrt before any charge; then use a non-gated model or text only."New value: +"Only for a model that sends inputs to China or a US recipient without a documented basis, when the step carries images, clips, voices or faces. Means: this material shows or contains no real person other than the human using this account. Set it ONLY after the human has said exactly that for THIS step; never assume it, never reuse it for the next step. Not needed when the human has declared this material in the FilmLab app: the backend reads that declaration, also for material derived from it; only the app can store one. An LK reference, a licensed likeness or another person's agreement does not replace it. Without it the backend refuses with drittland_dritte_gesperrt before any charge; then use a non-gated model or text only."
  2. Changed1 schema field changed
    • addedInput schema / properties / nur_eigene_daten
      Added value: +{
+  "description": "Only for a model that sends inputs to China or a US recipient without a documented basis, when the step carries images, clips, voices or faces. Means: this material shows or contains no real person other than the human using this account. Set it ONLY after the human has said exactly that for THIS step; never assume it, never reuse it for the next step. An LK reference, a licensed likeness or another person's agreement does not replace it. Without it the backend refuses with drittland_dritte_gesperrt before any charge; then use a non-gated model or text only.",
+  "type": "boolean"
+}
  3. Changed1 schema field changed
    • addedInput schema / additionalProperties
      Added value: +false
  4. Added

TDQS

A4.3/5.0
Behavior5/5

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

Despite readOnlyHint already covering the safety profile, the description adds substantial non-obvious behavior: a 20-minute per-source cap, first-call transcription via Fish Audio at ~0.36 USD per audio hour billed to the operator rather than the caller's credits, free cached repeat calls, and a 300 s per-page return limit. It also discloses the gating failure mode (drittland_dritte_gesperrt before any charge) and the ASR caveat about names being spelled phonetically.

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?

A single front-loaded paragraph that leads with what is returned and follows with sources, use cases, limits and cost. Most sentences earn their place, though the pricing/billing parenthetical is longer than the decision it supports needs.

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 tool with 8 parameters, no output schema and no annotations beyond readOnlyHint, the description covers sources, limits, cost model, caching, paging and a quality caveat — enough to call it correctly. The misleading `weiter_von_s` continuation hint and the absence of any statement about what a page item looks like keep it from the top score.

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 already 100%, so the baseline is 3; the description restates the source-selection rule and adds pagination semantics. However it instructs the agent to continue with `weiter_von_s`, a parameter that does not exist in the schema — the actual fields are von_s/bis_s — so the one piece of added parameter guidance is actively inconsistent with the input contract.

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?

"Every spoken word with its start and end time" names a concrete resource and output shape, and the parenthetical enumeration of the three accepted sources (video_id, audio_id, project_id + asset_key) makes the scope unambiguous. It is clearly distinguishable from siblings such as lab_wellenform (waveform) and lab_dub: this is transcript-level word timing.

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?

It gives three concrete scenarios (cutting pauses, timing captions, landing graphics on a word) and contrasts them with a named inferior approach — "instead of guessing seconds from the waveform" — which implicitly routes the agent away from the waveform tool. It does not name a sibling tool explicitly or state when not to use it (e.g. silent media, sources over 20 min).

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

All FilmLab toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources