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

Annotations declare a non-readonly, non-destructive, non-idempotent operation but say nothing about caching. The description adds real behavior: "Matching app context and screenshot paths reuse cached candidates," plus the explicit statement that no variant is created and no picker is opened. There is mild tension with idempotentHint=false (repeat calls sound cheap), but since the tool still writes cache state this is not a contradiction. Rate limits, permissions, and cache invalidation are unaddressed.

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 core action, the return payload, the caching rule, and the non-effects, front-loaded in that order. No filler. Minor cost: "app context" is an undefined concept that appears without explanation, and the returned fields are restated despite an output schema existing.

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?

An output schema exists, so return values need not be explained here, and all four parameters are fully documented in the schema. The description covers the caching/reuse model and the explicit non-effects. What is missing is routing guidance to apply_social_graphics_style and its screenshot-style sibling, which matters for an agent choosing among the prepare/apply/browse triad.

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 each parameter carries its own description (including the 1-7 vs 3-7 path rules per format), so the baseline is 3. The description adds one genuinely extra data point — that matching screenshot paths drive cache reuse — but says nothing about how "app context" is derived or how projectId/generationId aliasing interacts with caching.

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: "Generates or reuses personalized layout candidates across supported social, store-creative and ad formats," which scopes it to the social-graphics family rather than screenshot styles. It also states the negative effect ("Preparation does not create a variant or open a picker"), which separates it from apply_social_graphics_style/create_variant. It never names the closest sibling, prepare_screenshot_styles, so the differentiation is inferred rather than spelled out.

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?

"Preparation does not create a variant or open a picker" is a useful when-not, implying this is a pre-step before apply_social_graphics_style or create_variant. However no alternative is named, and there is no statement of when to call this versus prepare_screenshot_styles or browse_social_templates. Usage is implied rather than guided.

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