Product sizzle (music-led)

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

Despite no annotations (all false), the description fully discloses expensive nature (≈1,040 credits at 1080p), that the hero clip is the only paid leg, that dicing/cards are free, and that the music bed is included. It also reveals subtle behaviors like the paid hero always being 15s regardless of 'seconds', and the requirement for a real packshot to get the label right. No contradictions with 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?

Though longer than typical, every sentence earns its place: purpose, mechanics, cost breakdown, prerequisites, and alternatives. The structure is front-loaded with purpose, then details, then cost, then exclusions. No fluff; the length is justified by the complexity and cost sensitivity.

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?

The description thoroughly covers purpose, usage, costs, and alternatives. The only gap is that it doesn't state what the tool returns (e.g., a job ID, a video URL, or a completion status). Given the presence of sibling tools like get_job and list_jobs, an agent might infer async behavior, but this is not explicit. Everything else needed to call it correctly is present.

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?

Although schema covers 100% of parameters, the description adds crucial meaning: resolution cost tables, the fact that 'seconds' only affects packing not the paid render, aspect ratio fallback behavior, and the explicit recommendation on refImage. This goes beyond the schema's simple type/format explanations and helps the agent make cost-aware decisions.

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 the verb 'Render', the resource 'PRODUCT SIZZLE', and precisely describes the output: an 18-30s music-led video made from a single 15s Seedance hero clip, diced into cuts with typeset spec/CTA cards. It clearly differentiates from siblings by naming render_ad, generate_avatar, and make_template_ad as alternatives with distinct use cases.

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 when-to-use conditions: for talking/UGC use render_ad or generate_avatar, for cheap deterministic format use make_template_ad. Provides essential prerequisites: pass a real packshot as refImage, confirm spend with user before calling. Also clarifies cost implications and resolution trade-offs.

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