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

With readOnlyHint=false, the description correctly indicates a mutating operation (video to depth map). It adds valuable behavioral context: billing per second, immediate task_id return, asynchronous processing with polling, and automatic token refund on failure. This goes beyond the annotation and is transparent about cost and failure behavior.

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?

The description is compact yet dense, covering purpose, input options, billing, async workflow, and failure handling without fluff. Each clause contributes meaningful information. It could be slightly shorter, but the structure is logical and front-loaded.

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 an async creation tool with no output schema, it covers the key workflow: what it produces, how to pass videos, billing implications, immediate task_id, polling via get_depth_map_status, and token refund on failure. It doesn't describe the response JSON structure, but that's not necessary given the status tool and the task_id return.

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% and the schema descriptions already explain that video_url can be an external URL or a Switch video id, and duration_seconds is required for external URLs. The description reinforces this but does not add significant new parameter-level detail beyond the schema's own descriptions.

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 uses a specific verb ('Turn a video into') and clearly defines the output as a depth map, a grayscale video encoding distance. It distinguishes this from sibling tools like get_depth_map_status (status polling) and analyze_video by focusing on depth map generation.

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?

The description clearly explains how to provide input via external URL or own Switch video ids, naming list_my_videos and list_my_assets for retrieving ids. It also specifies when duration_seconds is required and points to get_depth_map_status for polling. It lacks an explicit 'when not to use' but the context is sufficient.

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