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

Annotations only declare this is a non-read-only, non-destructive write. The description adds three non-obvious behavioral facts the agent cannot get elsewhere: points equal to budget are reserved up front and refunded if unused, an authorization key is required, and the package/input/settings must match the quote. This is materially richer than the annotation set.

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?

Four compact sentences that front-load the consent precondition before the billing and permission details. No filler, though the ordering could surface the permission requirement slightly earlier.

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?

Covers preconditions, billing behavior, and authorization for a 13-parameter write tool with a nested input object and no output schema. It never indicates what a successful call yields (e.g. a run id), which is the main remaining gap given the absence of an output schema.

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 description coverage is 100% and all 13 parameters (including the enum policies and idempotency_key) are documented in the schema, so the baseline is 3. The description reinforces budget semantics (reservation and refund) and the quote-consistency requirement for input/package, but adds little beyond what the schema already states.

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 concrete verb+resource ('제작을 시작합니다') and makes the quote→start relationship explicit ('견적 때와 같은 package·input·설정을 보내야 합니다'), which cleanly separates it from the sibling vidia_quote. It stops short of naming vidia_quote outright, so the routing is implied rather than stated.

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 a hard precondition and implicit exclusion: call only after the quote has been shown and the user has consented ('보여 주고 동의를 받은 뒤에만 부르세요'). It also requires the '제작 시작 허용' permission key. It does not name an alternative tool for the estimate step, so the when-not-to-call guidance is strong but not complete.

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