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

Adds real cost and safety context beyond the annotations: 13 credits per image, a confirmCredits pre-authorization rule, and free retries via requestId (consistent with idempotentHint=true). It does not disclose any output or what an 'AI fit check' produces, and the price formula references a 'copies' factor that no schema parameter exposes, which muddies the arithmetic an agent must satisfy.

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, front-loaded with the price, which is the highest-salience fact for an agent. The middle formula sentence is dense and slightly self-undermining because of the undefined 'copies' term, but nothing is padding.

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 5-parameter credit-spending mutation with no output schema and no annotations on cost, the description covers the two things an agent would otherwise get wrong: how much it costs and how confirmCredits/requestId behave. Return values aren't needed for correct invocation, and remaining schema details are enforced by the schema itself.

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 full burden, and it explains only confirmCredits (must equal items x copies x variants) and requestId (retry is free). itemIds, projectId, and variants get no semantic explanation, and 'copies' is introduced as a price factor with no corresponding parameter, leaving the required confirmCredits value genuinely hard to compute.

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?

The description states a specific action and artifact: 'Makes low-cost previews with an AI fit check' at 13 credits per draft image, which is meaningfully different from a full render. It implies the split from the 'generate' sibling by contrasting drafts with 'finals' being bought later, but never names the alternative tool explicitly.

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?

'so finals are only bought for what works' gives a clear decision rule: draft first, promote selectively. What's missing is a named next step (generate vs approve vs get_status) and any exclusion such as when to skip drafting and go straight to finals.

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