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

Far exceeds the annotations: it discloses that confirm=true is mandatory because the change hits every page, that the write is idempotent-by-name (re-pushing the same name updates in place), that success must be read from `rendered` rather than the status code, that verification fetches the front page, that the connector injects on wp_head/wp_body_open/wp_footer with no Elementor Pro dependency, and that snippets live in XeoRank rather than Elementor's Custom Code UI, with a v0.9.2+ requirement. This is exactly the operational context annotations cannot carry. Minor tension: the description calls `name` an 'IDEMPOTENCY KEY' while idempotentHint=false, but the described behavior is update-in-place on repeated calls, so this reads as a conservative annotation rather than a true contradiction.

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?

Front-loaded with the core action and the one-snippet convention, then interleaved with routing and verification guidance. Dense and mostly earned, though the CHOOSING THE RIGHT HOME block and the connector/version sentences make it longer than a strictly minimal definition — justified by tool complexity, but not maximally tight.

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 destructive, 9-parameter, no-output-schema mutation, the description covers the gaps that matter: the mandatory confirm flag, how to interpret the response (`rendered` vs status code), the fallback-path limits on `conditions`, and environment prerequisites. 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 100%, so the baseline is 3, but the description adds real meaning: `name` as the update-in-place key, `confirm=true` as the per-page blast-radius gate, and the note that without narrower `conditions` the snippet injects everywhere. It does not restate the injection-location or priority semantics beyond the schema, keeping it just above baseline.

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?

Names a specific verb+resource (inject site-wide CSS/JS) and immediately fixes the scope (every page) and the single-snippet convention (CSS in <style>, JS in <script> in the same `code` body). It actively distinguishes itself from siblings by name: wp_set_brand_kit(custom_css) for editor canvas, wp_patch_page(style.custom_css) for element-scoped CSS.

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?

Explicit when-to-use ('anything the brand kit's design tokens cannot express', with a concrete list of examples, plus analytics/third-party embeds) and explicit when-not (prefer brand-kit tokens; use brand kit or page patching elsewhere). The CHOOSING THE RIGHT HOME sentence routes the agent among three sibling tools with the discriminating condition for each.

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