Rendu : capture d'image et file d'attente

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

With no annotations, the description carries the full burden. It discloses that images are costly in context and persist for the conversation, advises on verification frequency, and explains behavioral details of includeImage (auto-false beyond 3 timestamps returns paths) and maxDimension cost scaling. This is strong, though it doesn't cover every edge case (e.g., queue/start failure modes), so a 4 is appropriate.

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 compact sentences that front-load the core purpose and seamlessly integrate usage guidance with parameter nuances. Every clause earns its place; no fluff or repetition. The structure is efficient and highly readable.

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 tool with two operation modes, the description covers the key operational contexts (cost, verification strategy, maxDimension handling) and mentions queue/start. It doesn't fully describe the queue/start workflow or return details, and there's no output schema, but the schema handles most parameter specifics. Given the complexity, it's fairly complete, though a note on return behavior for queue/start would round it out.

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 high (87%), but the description adds significant value beyond it. For action, it explains the two operation families; for maxDimension, it explains the token cost and recommends defaults; for includeImage, it clarifies the automatic behavior beyond 3 timestamps. These insights are not present in the schema, making the description essential for correct usage.

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 clearly states the tool's dual purpose: action=snapshot renders and returns an image of the composition at a given moment (the visual verification loop), while action=queue/start control After Effects' render queue. It uses specific verbs and a clear resource (composition, render queue) and distinguishes between the two action modes, making it easy for an agent to know what to expect.

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?

Provides explicit usage guidance: verify after a block of operations rather than each keyframe, keep maxDimension low (default 700) unless inspecting details, and explains the cost/context implications. It also clarifies that queue/start handle the render queue. Though it doesn't name alternative tools, it gives actionable when/how to use guidance that directly informs tool selection.

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