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

Annotations already declare it is not read-only, is open-world, and is idempotent; the description adds high-value context beyond that: cost of 3 credits, refund on failure, two aspect-ratio outputs, and asynchronous polling. One gap remains: with idempotentHint=true but credit spend involved, it does not clarify whether a retried call spends more credits, which is exactly the kind of ambiguity an agent needs resolved.

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, each carrying useful information: scope and formats, cost/refund, and the polling instruction. The critical cost and async-follow-up facts are front-loaded rather than buried.

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 paid async generation tool with no output schema, the description covers the essentials: duration, formats, cost, failure refund, and the polling tool. It could be more complete by stating that two video assets are produced per call and by clarifying retry/credit behavior, but nothing essential to a correct first call is missing.

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 only 50%: confirm_spend is documented in the schema, but adaptation_id has no description there. The description implies 'one adaptation' but does not explain what an adaptation ID is or where to obtain it, so it only partially compensates for the uncovered parameter.

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 ('Start an 8-second video ad'), plus the exact output scope: one adaptation rendered in both 9:16 and 16:9. It also names the sibling used for follow-up (check_videos), so an agent can distinguish this from generate_adaptations or process_image 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?

Gives clear context: this is a paid generation action that must be followed by polling with check_videos, and it operates on one adaptation. It does not explicitly say when not to use it (e.g., existing videos should be listed via list_adaptations instead), so the exclusion boundary is left implicit.

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