Skip to main content
Glama
Sign In
viraldar

viraldar

by ThomasRayvol
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Local

Incruster texte et sous-titres

montage_texte

Adds text overlays and SRT or segment subtitles to videos in TikTok-safe zones, with automatic line wrapping, centering, timing checks, and a visual control sheet.

Instructions

Incruste des textes (accroche en haut par défaut) et des sous-titres (fichier SRT ou segments) dans la zone sûre TikTok du cas zone (par défaut « description » : x 86–907, y 403–1382 px sur 1080×1920, avatars à gauche évités ; voir montage_infos pour les autres cas). Coupure des lignes automatique, centrage sur l'axe de la zone. Prévient si un texte reste moins de 0.25 s par mot (2.5 s au moins). Rend aussi une planche de contrôle (-controle.jpg : une image par texte, zones tracées) quand un Chrome/Chromium est trouvé : regarde-la. Repère 1080×1920 : mettre d'abord la vidéo au format TikTok. Les emoji en couleur ne sont pas rendus (libass).

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": {
      "fichier": "<fichier>"
    },
    "name": "montage_texte"
  }
}

Input Schema

NameRequiredDescriptionDefault
nomNoNom de sortie (sans extension), rangé dans montages/.
fondNocontour par défaut ; boite = pavé façon TikTok
grasNooui par défaut
zoneNoZone sûre : description, sans_description, pub (défaut « description » ; détail dans carrousel_modeles ou montage_infos).
fonduNooui par défaut
policeNoPolice installée (Arial par défaut).
textesNoAccroches et textes posés.
couleurNo#RRGGBB (blanc)
fichierYesVidéo (de préférence déjà en 1080×1920).
qualiteNonormale par défaut.
controleNoPlanche de contrôle (oui par défaut).
sousTitresNoOu des segments (s).
couleurFondNo#RRGGBB(AA) (noir)
tailleTexteNopx (72)
sousTitresSrtNo.srt
dossierPolicesNoDossier de .ttf/.otf en plus.
tailleSousTitresNopx (58)
positionSousTitresNobas par défaut

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.1/5.0
Behavior3/5

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

With no annotations, the description must carry the full behavioral burden. It does well on surprising traits — safe-zone geometry, automatic line wrapping/centering, the under-0.25 s-per-word warning, the Chrome-dependent control JPEG, and the libass emoji limitation — but never says whether the source video is overwritten, where the rendered output lands, or how long a render takes for a mutation of this weight.

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?

Dense but front-loaded: purpose and output first, then geometry, then caveats. Every clause carries information, though the long parenthetical coordinate block and the trailing emoji/format reminders make it a heavy single paragraph rather than a scannable structure.

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 an 18-parameter render tool with no annotations and no output schema, the description covers the non-obvious essentials: zone semantics, prerequisite resolution, control-board artifact, and rendering limitation. Remaining gaps are output location and overwrite behavior, which matter but are secondary to getting the call right.

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%, so the baseline is 3; the description exceeds it by explaining what `zone` actually means (pixel bounds 86–907 × 403–1382, avatars avoided, alternatives in montage_infos) and by stating the default top position for `textes` and the 0.25 s/word timing threshold. It still leaves `qualite`, `fondu`, and `controle` purely to 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?

Opens with a specific verb ("Incruste") and names both resources it handles (textes / sous-titres) plus the scoping concept (zone sûre TikTok du cas `zone`). The task is unmistakable and clearly distinct from assembly, cutting, or format-conversion siblings.

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?

Gives an explicit prerequisite ("mettre d'abord la vidéo au format TikTok" en 1080×1920) and routes to montage_infos for the other `zone` cases. It also prescribes a post-step ("regarde-la" for the control board) but never states when this tool is *not* appropriate or names the format sibling it depends on directly.

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