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

Annotations already declare openWorldHint=true, idempotentHint=false, readOnlyHint=false, so the write/external nature is covered; the description adds the non-obvious credit-spend gate requiring explicit user agreement. It also discloses the async job pattern (returns an id, then poll), though it leaves slight ambiguity about whether the pre-confirmation call creates anything or only quotes a price.

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 dense sentences, each carrying distinct information: capability and tool list first, the credit-confirmation workflow second, the return value and follow-up last. No filler or restated title.

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 correctly supplies the return contract (video id) and the next step (poll get_video). For a 15-parameter, multi-mode tool it covers the critical decision points, but it doesn't clarify which params are mandatory per tool (e.g. product_image_url, logo_image_url, voice/script) or how ratio interacts with tool choice, leaving some trial-and-error.

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 high (87%) with enums for tool, voice, language, duration, and quality, so the description only needs to add routing meaning. It does add cross-call semantics for confirm_credits ("the exact cost the user agreed to, from the previous call") and scopes several params to specific tools (voice/script/captions/language to UGC creator, headline to caption/3D text, quality where offered and pro costs more).

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 ("Starts a product video") and enumerates the style-based tool families it covers (UGC creator, product ads, product with model, product effect, studio, 3D text, animated logo). This makes it clearly distinct from get_video, list_styles, and estimate_cost.

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 an explicit two-step procedure: call first without confirm_credits to obtain the cost, get user confirmation, then call again with confirm_credits set to that exact cost. It also names the follow-up action ("poll get_video"), so the agent knows the full lifecycle rather than just the single call.

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