Download a finished video

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

Annotations only declare openWorldHint, leaving the description to carry most of the behavioral burden. It does disclose the side effect (writes a file to the output directory) and the expiry constraint on result URLs, but says nothing about auth requirements, overwrite behavior if the file already exists, or error/timeout handling.

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 short sentences, front-loaded with the core action and destination, then optional behavior, then the urgency constraint. No filler or repetition.

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 and only openWorldHint in annotations, the description covers the essentials (destination, optional wait, expiry) but omits the file naming/return value and any failure modes. Adequate, but an agent still has to guess at specifics after the call.

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 description coverage is 50%: wait_seconds is fully documented in the schema, while task_id is undocumented there. The description's 'waits for the task first' merely restates wait_seconds and never clarifies what task_id is or where to obtain it, so it does not compensate for the coverage gap.

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 states a specific verb ('Saves') and resource ('a completed Modelflare video') plus the destination ('the output directory'), so an agent can distinguish it from create_video and get_video_status. It stops short of naming or explicitly contrasting any sibling, which keeps it from the top band.

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?

'Optionally waits for the task first' and 'download soon after completion' give clear context on when to call this (post-completion, promptly, with an optional wait). There is no explicit exclusion or named alternative such as checking get_video_status first, so it falls 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.