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

Annotations only flag it as a non-read-only, open-world, non-idempotent, non-destructive operation; the description goes well past that by disclosing a 10-15 minute generation time, price and refund-on-failure semantics, and the fact that an unreadable social URL is refused before anything is charged. Those are the failure and cost behaviors an agent needs before spending money, none of which appear in annotations.

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?

It is a single dense block with the core purpose front-loaded and no filler or marketing padding — every clause carries operational information (structure preservation, product branch, URL constraint, price, duration, polling). It loses a point only for being a long run-on paragraph whose within-sentence ordering could be tightened.

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 six-parameter, cost-incurring, asynchronous generation tool with no output schema, the description covers everything an agent needs: input validation rules, cost and refund behavior, expected latency, and how to retrieve results via list_clips. Nothing material about calling it correctly is left unstated.

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%, so a baseline of 3 applies, but the description genuinely adds decision-level meaning: it explains that topic is only meaningful without product_id, what happens if topic is omitted, and that reference_url must be a direct file or /u/... link rather than a social post page. It leaves captions, character_id and note entirely to the schema, which is acceptable given their self-explanatory 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 first sentence names a specific verb and resource (turn a proven video into a new clip) and describes the mechanism precisely: the engine watches the reference, extracts hook/story beats/timings, and writes new lines on that structure without reusing the reference's people or brand. That mechanism is what distinguishes it from siblings like generate_clips, create_video or copy_motion, so an agent can pick it 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?

It spells out both branches of use: with product_id the clip stars a catalog product, without it the clip sells nothing and topic either supplies a subject or falls back to the reference's own topic. It also names prerequisites (product id from list_products), an explicit exclusion (TikTok/Instagram/YouTube post pages are refused), the pricing analogue (generate_clips), and the follow-up action (poll list_clips for download links).

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