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

Annotations are minimal (readOnlyHint=false, idempotentHint=true), and the description adds substantial behavioral context: immutability of the new design, requirement for prior authorization, the fact that prior approval does not carry over, idempotent retry semantics via requestId, return of previews and a new designToken, and the caveat about changed templates. This is exactly the kind of behavioral disclosure that helps an agent avoid misuse.

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?

The description is compact but information-dense, with no filler. Each sentence delivers a distinct operational requirement: base design, complete fields, requestId semantics, return values, approval non-transfer, and template-change fallback. The most important constraint about creating a new immutable design is front-loaded.

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 tool with non-obvious behaviors around immutability, idempotency, guest vs. authenticated flows, and approval carry-over, the description plus schema covers all critical aspects. Even without an output schema, it states what the caller gets: previews and a new designToken. No essential usage information is missing for an agent to invoke it correctly.

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 already high (80%), and the description adds valuable parameter semantics beyond the schema: complete field set required, logo passed via logoUrl only when the template has an imageUrl field, new requestId for intentional edits versus same id for retries, and guestToken usage constraints. The designToken parameter is less elaborated, but the description clarifies it as both an input and a newly returned token.

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 operation: 'Create a new immutable design from an authorized prior design, using the same published template revision.' This clearly distinguishes the revision action from creating a fresh design and from merely refreshing a proof. The title and description align without any circular phrasing.

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 concrete usage context: use it for intentional edits to an authorized prior design, and explicitly says not to use it as a partial patch. It also provides an alternative route: 'If the template changed, select its current version and create a new design.' It does not explicitly name sibling create_business_card_design, but the behavioral boundary is clear.

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