WACrew

ver_video

Samples frames from a video or GIF so the AI can understand its visual content; if no media path is given, it shows the group's last video or GIF.

Instructions

Mostra um vídeo ou GIF pra IA enxergar, amostrando alguns frames (via ffmpeg). Use pra entender o conteúdo visual de um GIF (reação/meme) ou de um vídeo mudo. Para o áudio do vídeo, use 'transcrever'; pra entender imagem e fala juntos (ex.: cliente mostrando um erro), use 'assistir_video'. Sem mediaPath, mostra o ÚLTIMO vídeo/GIF do grupo.

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": {
      "grupo": "<grupo>"
    },
    "name": "ver_video"
  }
}

Input Schema

Name	Required	Description
`grupo`	Yes	slug do grupo
`frames`	No	nº de frames a amostrar (default 3)
`mediaPath`	No	mediaPath da mensagem (campo 'midia'); ausente = último vídeo/GIF do grupo

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 14, 2026

TDQS

A4.4/5.0

Behavior4/5

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

With no annotations, the description carries the full burden and does well: it discloses the mechanism (ffmpeg frame sampling), the default sampling size, the fallback behavior when mediaPath is omitted, and implicitly that this is a read/inspect operation. It stops short of stating what is actually returned (list of frame images) or limits/failure modes for unsupported media, which keeps it from a 5.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Front-loads the core action, then alternatives, then the default-behavior rule, in three tight sentences with zero filler. Every clause carries either a capability or a routing decision.

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 3-parameter media inspection tool with no annotations and no output schema, the description covers purpose, boundaries, and the important default. The only real gap is the return shape (that it yields sampled frame images the agent can look at), which matters slightly given no output schema exists.

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 description coverage is 100%, so grupo, frames (default 3, max 8) and mediaPath are already documented in the schema. The description only restates the mediaPath default ("ausente = último vídeo/GIF do grupo") and adds no format or syntax detail beyond that, so baseline 3 applies.

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 verb and resource ("Mostra um vídeo ou GIF", "amostrando alguns frames via ffmpeg") plus the scope (visual content only, no audio), and explicitly names the sibling tools it is not ("transcrever", "assistir_video"). An agent can distinguish it from every nearby tool without opening a 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 explicit when-to-use cases (GIF reaction/meme, muted video) and routes the agent away with conditions: audio → 'transcrever', image+speech together → 'assistir_video'. It also covers the no-mediaPath case by defaulting to the group's last video/GIF, so no decision is left to inference.

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