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

The annotations already mark the tool as destructive and non-idempotent, but the description adds substantial context: omitted controls are preserved, custom_css replaces the entire draft, reset_only settings are retired, device reset affects inheritance, and the operation does not publish. This is rich guidance beyond the annotations and is consistent with them.

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 dense but appropriately front-loaded: purpose first, then prerequisite, then behavioral rules. Most sentences earn their place, though the long paragraph could be more scannable if broken into bullets.

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 complex, destructive draft-editing tool with no output schema, the description covers the key behavioral constraints an agent needs: prerequisites, draft-only scope, non-publishing behavior, device inheritance, reset semantics, and replacement behavior for custom_css. It is complete enough to select and invoke the tool 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?

With only 50% schema description coverage, the description meaningfully compensates: it explains that values are strings including numbers, how device targeting works, the two reset forms and inheritance behavior, and that custom_css is a full replacement. It does not cover every schema detail such as the 250-item limit, but it adds strong semantic value where it matters.

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 verb and resource: saving native Design Studio changes as a draft. It immediately distinguishes the tool from publishing with 'Does not publish,' so an agent can separate it from publish_design 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 explicit usage guidance: use only when requested, read get_design first for supported keys/ranges/choices/revision, and use existing editors for theme switching, legacy palettes, branding, and page-specific overrides. These are clear when-to-use, prerequisites, and exclusions.

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