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

Goes well beyond the annotations: it discloses that preview is free of export allowance while export consumes it, that output is deterministic, that download links are short-lived, that exports are subject to opacity/file-type/file-size limits and may be ZIPped, and that saved layouts are not modified. Those quota, artifact-limit, link-lifetime and non-mutation facts are exactly what an agent needs before calling a non-readOnly, non-idempotent tool.

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 tight sentences, front-loaded with what it renders, then the mode trade-off, then output constraints and link lifetime. Every sentence carries distinct information; the closing 'Does not modify saved layouts' is a deliberate safety note, not filler.

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 an output schema present, the description needn't explain return shapes, and it covers mode semantics, quota, limits and non-mutation well. The main remaining gap is how to identify the layout to render (variantId vs generationId/projectId), which the description never addresses despite being the highest-risk selection decision.

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 only 43%, but the description does add real semantic weight for the two enum parameters: it defines what 'preview' and 'export' actually mean in cost and output. It says nothing about variantId (undocumented in the schema too), projectId/generationId aliasing, platform, or languages, leaving several parameters to the schema alone.

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?

Specific verb+resource with scope: 'Renders saved or derived social/store-creative layouts deterministically', and it splits the tool into two named modes (preview/export). It does not name the neighbouring render/export siblings (render_screenshots, export_promo_video, export_mockup_animation), so an agent must infer the boundary from the 'social/store-creative' scope alone.

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?

The description gives strong internal routing ('preview mode returns inspection images and does not consume export allowance' vs export consuming allowance), which effectively tells the agent when to pick each mode. However, it never says when to use this tool versus sibling render/export tools, and no prerequisites (variants must exist, project scope) are stated.

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