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

With no annotations, the description carries the full burden and does so: 'Nothing is saved — the design's environment is swapped on a scratch copy for each cell', a 16-cell ceiling, output as a short-lived signed https link kept under 3.5 MB, `inline: true` returning bytes, and the native/masked rendering condition tied to the ui-builder-export grant. These are exactly the traits an agent needs and none are derivable from the schema.

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 key value proposition is front-loaded in the first clause, but the body is a single dense run-on that re-enumerates all 17 device presets already present in the schema enum, which is redundant with structured data. The remaining content earns its place, but the wall-of-text form and duplicated enum hurt scanability.

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 10-parameter tool with no annotations, the description covers the important unknowns: output form and size cap, the no-persistence guarantee, the 16-cell limit, and the conditional native-rendering lane. With an output schema present it needn't explain return values, and the remaining parameter details (token, revision, agentName) are handled in the schema.

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 90%, so baseline is 3, and the description adds real meaning on top: it explains what each `formFactor` default set contains, how `themes`/`fontScales` cross-multiply against devices, and the at-most-16-cells constraint that governs the combination. It does restate the device preset enum, which the schema already lists.

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 names a specific verb and artifact — 'See one design on several devices in ONE picture: a contact sheet with a captioned cell per device × theme × font scale' — and the scratch-copy/no-save scope implicitly separates it from ui_builder_render_native and ui_builder_export. An agent can tell what this produces without opening the schema.

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?

It gives concrete selection rules for inputs: name `devices` by preset or {widthDp,heightDp}, or pass a `formFactor` for its default set, and with neither you get the design's own form factor (with per-family defaults spelled out for mobile, Wear and Wear widgets). It also states the native-vs-editor lane condition (caller must hold ui-builder-export). What's missing is any explicit routing to a sibling tool for the cases this one doesn't cover.

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