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

Annotations declare the mutation and idempotency profile, and the description adds genuinely new behavior: the create-if-missing fallback, the partial-failure mode with `code: "embed_install_failed"` where the widget stays on and the owner must be told it isn't on the site yet, and the fact that visitors only see it after the next publish. That partial-success semantics is exactly what an agent needs and is nowhere in the annotations.

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 verb and resource, then the multi-step behavior, then the failure mode and the scope boundary — a sensible order with no filler. The parenthetical description of the widget is slightly promotional but still earns its place by defining the resource.

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 3-parameter mutation with no output schema, the description covers the important return behavior (partial failure code, post-publish visibility) and where other widget configuration lives. It leaves out prerequisites such as permissions or whether the widget requires an addon/plan, which is a real but modest gap.

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 description coverage is 100%, so site_id, user_goal and welcome_message are already documented, including the 'omit to keep the current one' behavior. The description adds only a hint that a brief is drafted from the site on creation, which doesn't clarify any individual parameter. Baseline 3 is appropriate when the schema carries the parameter load.

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?

States a specific verb and resource ('Turn on a site's chat widget') and immediately defines what the widget is and what it does. It also makes the sub-operations explicit ('creates it when the site has none... switches it on... installs it'), which lets an agent distinguish it from disable_chat_widget and get_chat_widget_status without opening any 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?

Clear context for when this is the right call: the widget is absent or off, and the agent wants it live in one call. The closing line routes appearance, chat flows and knowledge configuration out to the editor, which is a useful boundary. It doesn't name a sibling alternative explicitly (e.g. get_chat_widget_status to check first, or an addon requirement), so it stops short of full when/when-not guidance.

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