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

The annotations already flag destructiveHint=true, idempotentHint=false, and openWorldHint=false, but the description adds real causal detail beyond them: platform switching rewrites device frames/models and single-store badges across saved formats and languages, and on single-platform projects it also changes the project-level platform shared by the screenshot editor. That is exactly the kind of blast-radius disclosure needed for a destructive mutation. It stops short of stating whether changes persist immediately or require a subsequent save/render.

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 scope statement is front-loaded, and the second sentence packs two distinct behaviors into a single readable clause. Slightly dense but no filler or restated title.

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, and the destructive nature is covered. But for a mutation with zero required parameters and five optional ones, the description gives no guidance on defaults, minimum viable parameter sets, or what state the settings must be in before calling — gaps an agent would hit immediately.

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 40%: projectId and generationId are self-documented in the schema, and the description meaningfully explains primaryFormat (default format across languages) and platform (device frames/models, badges, project platform on single-platform projects). However, variantId — arguably the most central parameter for a "variant-wide" update — is undocumented in both schema and description, and no guidance is given on which optional parameter combinations are valid or required.

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 first sentence names a specific verb and resource with scope ("variant-wide graphics settings"), and the following sentences enumerate the two mutable axes: default format and platform. It is distinguishable from save_graphics / save_graphics_format, though the description never explicitly contrasts them.

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?

Usage is implied by the described effects (change default format across languages; change platform), but there is no explicit when-to-use or when-not-to-use statement and no routing to sibling tools such as apply_social_graphics_style or save_graphics_format. The agent must infer the trigger condition.

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