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

Annotations already flag this as a non-read-only, destructive mutation, so the description's job is to add context — and it does: merge-not-replace semantics, reset-to-defaults behavior, conditional field applicability (inset/radius only on floating), and the get_project cross-reference for reading state. It does not explain why the operation is destructive beyond reset, nor permissions/error behavior, so a 4 rather than 5.

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?

Dense but waste-free: nearly every clause maps to a distinct parameter or behavior, and the partial-update/reset guidance is placed near the end where it belongs after the field semantics. The trade-off is a single semicolon-chained wall of text that is harder to skim than a short structured list would be for 15 parameters.

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 15-parameter mutation with no output schema, the description covers layout modes, transparency scope, tint/blur, all sticky sub-behaviors, conditional fields, update semantics, reset, and where to read current values. Nothing an agent needs to invoke it correctly is missing.

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 73% and several enum/boolean params (layout, sticky, transparent, onScroll partially) have no schema descriptions, yet the description supplies meaning for every one: floating as "an inset card with a top gap and corner radius," scope as hero vs all pages, onScroll hide as "slides away going down, back going up" and shrink as "tighter bars," plus mobileSticky's phone behavior. This is exactly the value-add over schema that this dimension rewards.

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?

Opens by identifying the exact resource — the site header, framed as the navbar section's Header settings that apply site-wide — which immediately distinguishes it from page-level setters like set_page_settings. Combined with the tool name and the enumerated layout/sticky/transparency options, an agent knows precisely what this configures.

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?

"Pass only what changes; reset: true goes back to the defaults" gives explicit partial-update semantics, and "uichemy_get_project shows the current settings as design.header" tells the agent to read before/after. It also states that inset and radius only apply to the floating layout, a real applicability constraint. It stops short of naming a sibling alternative for header editing or stating prerequisites, so not a 5.

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