Skip to main content
Glama
Sign In
WACrew

WACrew

by sumioshi
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

assistir_video

Analyzes video visuals and audio with Gemini, returning what appears and what is said with MM:SS timestamps. Use for chat attachments or YouTube, Instagram, TikTok links when content matters.

Instructions

Assiste um vídeo com o Gemini (imagem e áudio juntos) e devolve o que aparece e o que é falado, com tempos MM:SS. Use quando o conteúdo do vídeo importa: cliente mostrando erro na tela, explicando algo em vídeo, ou mandando LINK de vídeo (YouTube, Instagram, TikTok). Custa ~US$ 0,03–0,05 por minuto de vídeo (OpenRouter): chame sob demanda, nunca em lote. GIF/meme ou só uma olhada rápida: prefira 'ver_video' (grátis). Vídeo do chat: grupo + id (campo 'id' de ler_mensagens) ou mediaPath; sem os dois, o ÚLTIMO vídeo do grupo. Link: url (grupo opcional). pergunta foca a resposta. Teto: 20 min de vídeo.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "assistir_video"
  }
}

Input Schema

NameRequiredDescriptionDefault
idNoid da mensagem de vídeo (campo 'id' de ler_mensagens)
urlNolink do vídeo (YouTube, Instagram, TikTok…) em vez de um anexo do chat
grupoNoslug do grupo (obrigatório quando não há url)
perguntaNoo que você quer saber do vídeo; ausente = descrição completa
mediaPathNomediaPath do vídeo (campo 'midia')

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A4.8/5.0
Behavior5/5

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

With no annotations supplied, the description carries the whole burden and does so: it discloses the monetary cost (~US$ 0,03–0,05 per minute via OpenRouter), the batching prohibition, and a hard 20-minute ceiling. It also resolves the ambiguous case where neither `id` nor `mediaPath` is given, stating the tool falls back to the LAST video of the group — behavior an agent could not infer from the schema.

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, then triggers, then cost, then parameter routing — a sensible order with no filler. The telegraphic, backtick-heavy style packs a lot in but reads more like notes than prose, which costs a little clarity for an agent parsing it cold.

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?

For a five-parameter, no-annotation, no-output-schema tool, the description covers everything that matters: return format (on-screen + speech with timestamps), cost model, size limit, default selection behavior when IDs are omitted, and the cheaper alternative. Nothing an agent needs in order to call it 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?

Schema coverage is already 100%, so the baseline is 3, but the description adds real semantics: `grupo` is required when there is no `url`, `id` comes from ler_mensagens and `mediaPath` from the 'midia' field, and an absent `pergunta` yields a full description rather than a focused answer. Only minor gaps remain, such as whether `url` overrides an attached video if both are supplied.

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 ('Assiste um vídeo com o Gemini') and specifies the output precisely: what appears on screen, what is spoken, with MM:SS timestamps. It also explicitly separates itself from the sibling 'ver_video', so an agent can choose between them without opening either schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Gives concrete when-to-use triggers (customer showing an error on screen, explaining something on video, sending a video link from YouTube/Instagram/TikTok) plus an explicit when-not: GIFs, memes or a quick glance should go to the free 'ver_video' instead. The cost-driven rule 'chame sob demanda, nunca em lote' further constrains invocation.

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