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

Annotations already cover safety and idempotency, and the description adds real behavioral context beyond them: the 10-credit price per image, the rule that confirmCredits must match the computed total, and that requestId makes a retry free. That is the billing and retry behavior an agent needs before calling a paid mutation.

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 with the cost front-loaded and no filler; each sentence adds a distinct fact (price, purpose, confirmation/idempotency rules).

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 price, confirmation validation, and retry semantics for a paid mutation with no output schema. The shape of the returned drafts is not described, but the operative details an agent needs to invoke it correctly are 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?

Schema description coverage is 0%, so the description carries the burden; it explains confirmCredits (validated against items x copies x variants) and requestId (idempotency key) well, but leaves projectId, itemIds, and variants' allowed values (1 or 4) unexplained. Partial compensation only.

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 action (makes low-cost preview images with an AI fit check) and implicitly draws the boundary against buying finals, which separates it from the generate sibling. An agent can tell what this produces 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?

Explains when it is appropriate — cheap previews so finals are only purchased for what works — which is clear usage context. It does not explicitly name an alternative tool (e.g. generate for finals), so it stops short of full when/when-not routing.

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