Baixar mídia do Flow

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

Goes well beyond the annotations by disclosing that files ALWAYS land in a fixed path regardless of whether the caller is Claude Code or Claude Desktop, and that 1080p/2k are Flow-enhanced variants with the credit balance (saldo) checked before and after — a real cost side effect that annotations (readOnlyHint=false, destructiveHint=false) do not convey. It does not specify filename conventions or whether an existing file is overwritten, which matters for a disk-writing tool.

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?

Three sentences, front-loaded with the action and resource, then the destination path, then the quality semantics. The parenthetical '(vídeo estendido)' and the Claude Code/Desktop clause are justified because they disambiguate scene type and explain why the path is fixed. Slight redundancy in restating the destination twice.

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?

With no output schema, the description must convey the result, and it does only loosely — a directory path is given, but not the returned file name, whether a result payload lists the saved files, or what happens on collision. The path itself is garbled with mixed separators ('/app/%LOCALAPPDATA%\mcp-google/saidas/flow'), which an agent cannot reliably interpret.

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?

At 67% schema coverage the description carries real weight: it explains that 'original' is the file exactly as generated while '1080p' applies to video and '2k' to image and consumes credit. That adds meaning the enum alone does not. It omits the 'gif' enum value entirely, leaving one valid quality mode undefined in both places.

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 specific verb (baixa) and a precise resource scope: an image, video, or scene (extended video) already generated in Flow, retrieved by id. An agent can tell it apart from generation siblings (flow_gerar_imagem, flow_gerar_video, flow_estender_video) because the media must already exist. It does not, however, differentiate itself from nearby siblings like flow_arquivo or flow_estudio_baixar-style downloaders.

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?

Usage is implied by 'já gerada' (already generated), so the agent infers this is a post-generation retrieval step, but there is no explicit when-to-use statement, no mention that an id must first come from flow_listar, and no statement of when not to use it. The alternative among sibling downloaders 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.