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

Annotations declare destructiveHint=true, idempotentHint=true and readOnlyHint=false; the description goes beyond them with two operationally important facts not in structured fields: configure merges over current settings (so only changed keys need sending, and unmentioned settings survive), and changes only reach visitors on the next publish. That is exactly the kind of consequence an agent needs before mutating a live site.

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 action semantics, then settings examples, then the publish caveat — a sensible order with no filler sentences. It is a single dense paragraph whose long inline example list would be easier to scan as a list, which is the only thing keeping it off a 5.

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?

With no output schema, the description should imply results; it covers the publish-timing consequence well but does not say what happens to an add-on's settings on 'remove' (whether configuration is discarded or retained), which matters given destructiveHint=true. Otherwise complete for a 5-parameter mutation tool.

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 baseline is 3, but the description exceeds that by giving concrete settings shapes for four add-on kinds (announcement-bar, newsletter-popup, whatsapp-bubble, countdown), including enumerated color and trigger values — real value given the schema declares settings as a bare object with additionalProperties. It stops short of documenting the remaining six kinds (exit-popup, social-proof, cookie-banner, calendly-float, back-to-top, footer-attribution).

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 with a precise verb cluster ('Remove, switch off or on, or reconfigure') paired with the specific resource ('an add-on the site already has'), which maps exactly onto the four enum actions. It is clearly distinguishable from siblings like add_* or set_footer_credit, and it explicitly routes listing to list_site_addons.

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?

Names two alternatives and the condition that selects them: list_site_addons for discovering what exists, set_footer_credit for the agency footer credit (which is otherwise a valid-looking enum value here). It also states the semantic difference between disable/enable (settings preserved) and configure (merge), so the agent knows which action to pick.

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