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

Annotations only cover readOnly/destructive/openWorld hints; the description adds genuinely behavioral facts: asynchronous task_id return, std::poll workflow, typical few-minute latency, per-second billing, and automatic token refund on failure. That is exactly the context annotations cannot carry.

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?

Dense but front-loaded: the what/why comes first, then input rules, then the async/polling and billing consequences. Every sentence carries actionable information with no filler.

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 fully covers the return contract (task_id, poll get_depth_map_status, download URL, failure behavior). Nothing an agent needs to invoke and follow up correctly is missing.

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 already 100%, so the baseline is 3. The description restates the external-URL-vs-Switch-video distinction for duration_seconds that the schema description also makes, adding little new syntax or format detail beyond it.

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?

Names a specific verb+resource and defines the artifact itself ('a grayscale video where brightness encodes distance'), plus the downstream use case (motion reference for a generated subject). An agent can distinguish this from siblings like analyze_video or generate_video without opening the schema.

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?

Explains input options clearly (public https URL vs own Switch video id, sourced from list_my_videos/list_my_assets) and the duration_seconds rule for each path. It also routes the agent to get_depth_map_status for polling. It lacks an explicit 'when not to use this / use sibling X instead' statement, so it stops short of a 5.

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