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

Annotations only say it is a non-idempotent, non-destructive write; the description adds substantial behavior the annotations cannot: the call consumes one of the user's videos (two for Paper Collage), generation is asynchronous and takes 1-3 minutes before get_video returns links, at most 2 videos run concurrently, and free-trial output carries a watermark. These are exactly the operational constraints an agent needs before invoking.

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 nearly every clause carries information; the critical constraint (video consumption / say so first) is front-loaded. It is a single run-on paragraph, however, and the mode-selection rules would scan better as separated sentences or bullets.

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 10-parameter, no-output-schema generation tool, the description covers the full arc: inputs, prerequisites, latency, where results are retrieved (get_video supplies links, title, captions, hashtags), concurrency limits, and licensing/watermark effects. An agent can execute and follow up correctly without further reading.

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?

With only 50% schema coverage over 10 parameters, the description carries real weight: it explains the idea/script_id+lines pairing, clarifies that facts are strictly limiting ("the video only uses the facts it is given"), ties script_id to the edit case where style/voice/character are inherited, and notes character eligibility by style. It leaves 'voice', 'project' and 'keyword' (beyond 'sales video with keyword') unexplained, so it does not fully 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?

States a specific verb and resource ("Makes a video") and immediately enumerates the two input modes: from an idea (HypeFox writes the script) or from a script/edit produced by preview_script or preview_video_edit. It also names the downstream tool (get_video) and the prerequisite tools, so an agent can place this tool precisely in the workflow.

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?

Gives explicit routing rules: use idea when starting fresh, use script_id + lines with a preview_script result, and "To change a video that's already made always go through preview_video_edit, never an idea." It also states a consent obligation ("It uses 1 of the user's videos ... say so before calling"), which is a when-to-use condition rather than mere description.

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