Skip to main content
Glama

Colocar marca d'água no vídeo

aplicar_marca_dagua

Baixa o vídeo do link (mesmos sites do baixar_midia) e coloca a marca d'água de TEXTO do usuário, como @perfil ou o nome da loja. Padrões: letreiro (Passa de um lado ao outro da tela, sem parar.) letreiro-subindo (Sobe de baixo para cima pelo meio da tela, sem parar.) quicando (Anda pela tela e bate nas bordas. Ninguém corta.) troca-canto (Pula de canto a cada 2,5 s, como a do TikTok.) mosaico (Repetida em diagonal pela tela toda.) canto (Parada num canto, discreta.) centro (Grande e transparente no meio do vídeo.) Leva de 10 s a 1 min. Se ficar pronto na hora, devolve o link do MP4; se não, devolve um id: chame ver_marca_dagua com ele. Grátis 1 vídeo por dia por conta (somando site e IA); ilimitado no Premium. Pergunte o texto ao usuário se ele não disse.

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>",
      "texto": "<texto>"
    },
    "name": "aplicar_marca_dagua"
  }
}

Input Schema

NameRequiredDescriptionDefault
corNobranco
urlYesLink do vídeo, como o usuário copiou no app.
cantoNoSó para os padrões canto e troca-canto (onde começa).sup-dir
faixaNoSó para o letreiro (o que passa de lado): altura onde passa. O letreiro-subindo sobe pelo meio.meio
textoYesTexto da marca, até 40 letras (emoji sai). Ex.: @minhaloja
estiloNosombra (texto com sombra), etiqueta (fundo arredondado) ou contorno.sombra
padraoNoComo a marca aparece.letreiro
tamanhoNop, m ou g.m
opacidadeNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / faixa / description
      Previous value: -"Só para o letreiro: altura onde passa."New value: +"Só para o letreiro (o que passa de lado): altura onde passa. O letreiro-subindo sobe pelo meio."
    • changedInput schema / properties / padrao / enum
      Previous value: -[
      -  "letreiro",
      -  "quicando",
      -  "troca-canto",
      -  "mosaico",
      -  "canto",
      -  "centro"
      -]New value: +[
      +  "letreiro",
      +  "letreiro-subindo",
      +  "quicando",
      +  "troca-canto",
      +  "mosaico",
      +  "canto",
      +  "centro"
      +]
  2. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Adds substantial behavior the annotations cannot convey: processing takes 10s to 1min, the response is either a direct MP4 link or an id requiring polling via ver_marca_dagua, and there is a per-account daily free limit shared with the AI flow. This is exactly the async/quota disclosure an agent needs, and it is consistent with readOnlyHint=false and idempotentHint=false.

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: the action comes first, then the pattern catalogue, then timing, return shape, quota, and the ask-the-user instruction. Almost every sentence carries load, though the inline parenthetical pattern explanations make it feel run-on and could be tightened into a list.

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, and the description fully covers what comes back (MP4 link or job id plus the follow-up call). For a 9-parameter, non-idempotent mutation with quota constraints, the combination of timing, fallback path, and quota disclosure leaves nothing an agent needs 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 78% schema coverage the baseline is 3, but the description genuinely extends the enum semantics: it explains all seven padrao values in terms of on-screen motion (letreiro crosses the screen, quicando bounces off edges, troca-canto jumps corners every 2.5s like TikTok, etc.), which the schema only labels as 'Como a marca aparece.' It also gives a texto example and the 40-character limit context. cor, opacidade and tamanho remain undocumented in prose — tamanho's schema text ('p, m ou g') is circular.

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 concrete two-step action: downloads the video from the link (explicitly the same sources as baixar_midia) and overlays a TEXT watermark on it. Distinguishes itself from the sibling downloader by naming it and specifying the added transformation, so an agent can choose between them without opening schemas.

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 concrete operating guidance: ask the user for the watermark text if it wasn't provided, and after a submitted job call ver_marca_dagua with the returned id. Quota rules (1 free video/day per account, unlimited on Premium) frame when the tool will succeed. It stops short of an explicit when-not-to-use statement versus baixar_midia, which keeps it below 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources