Gerar vídeo no Flow

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

With annotations only saying it is a non-read-only, non-destructive open-world call, the description carries real weight: it discloses credit spend per model, that requests exceeding the daily quota are rejected before submission, the 1–3 minute generation time, and the ~50 s Desktop timeout that forces polling. It also fixes the output location. Nothing here contradicts the annotations.

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

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

Information is front-loaded: what it produces, where files land, cost, then the mode conflicts and the async caveat. It is dense but nearly every sentence carries operational meaning; the credit-cost sentence partly duplicates the modelo schema entry.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 15-parameter, long-running, credit-consuming generation tool with no output schema, the description covers cost, timing, async polling, file destination and mode incompatibilities. It stops short of describing the response payload shape in Claude Code (beyond 'waits and downloads'), which would help an agent parse results.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

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 still adds semantics the schema lacks, notably that elementos (personagens/referencias) are mutually exclusive with imagem_inicio/imagem_fim because they are different Flow modes. The credit-cost restatement and the default model repeat the schema's own parameter descriptions, which limits the added value.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

States a concrete verb and artifact ('Gera vídeo curto no Google Flow (Veo 3.1, 8 s com áudio)') plus the side effect of downloading an .mp4 with AI Pro credits. It distinguishes itself from siblings by naming flow_estender_video for durations beyond 8 s and flow_status for polling, so an agent can place it in the flow_* family immediately.

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

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

Gives explicit conditions: image-to-video via imagem_inicio/imagem_fim, elementos for character consistency, and that elementos do not combine with start/end images. It also explains the Claude Desktop vs Claude Code calling pattern. It never explicitly contrasts with flow_video_longo or notebook_gerar_video, which are the neighboring alternatives an agent might pick instead.

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