Extrair um quadro (encadear clipes)

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

With no annotations, the description must carry the full behavioral burden. It does disclose the core mutation (writes a JPEG to disk) and the output format, plus the chaining behavior of using the last frame. It omits overwrite/error behavior and any permission or timing constraints, so the disclosure is partial.

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?

Two tight sentences with no filler, and the what-it-does statement is front-loaded ahead of the chaining tip. The structure is efficient, though the chaining sentence could be trimmed without loss.

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 5-parameter write tool with no output schema and 40% parameter coverage, two sentences is thin. Several parameters go undocumented, and there is no mention of output path semantics or failure modes, so an agent is left guessing about width and project inputs.

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 only 40%, so the description should compensate. It clarifies the frame-selection semantics that map to 'posicao' (though the schema already documents those values) and implies 'video'/'saida', but it says nothing about 'largura' (width) or 'projeto', which remain undocumented 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?

The description gives a specific verb+resource ('Salva ... um quadro ... de um vídeo como JPEG') and specifies which frames can be selected (first, last, or a time in seconds). It is clear on its own, but it never distinguishes itself from the close sibling 'extrair_frames' (plural), which an agent could easily confuse with this single-frame tool.

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?

It provides one concrete workflow – use the LAST frame as start_image of the next clip to chain a continuous journey – which is genuinely helpful guidance. However, it gives no when-not condition and no explicit routing between this tool and 'extrair_frames' or 'analisar_video', leaving sibling selection to inference.

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