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

Goes well beyond the annotations by disclosing the key destructive consequence: the change 'goes live at once without publishing other pending edits.' It also explains the two-phase propose→confirm protocol, the exact status string returned, and the paid-plan gate with its blocked/upsell outcome — exactly the context an agent needs before invoking a destructive mutation.

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 and its scope, then prerequisites, then the confirmation protocol. Dense but each clause carries operational information. Slightly packed with quoted literals, though none are gratuitous.

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 mutation with no output schema, it covers the return status, the follow-up tool, the paid-plan gate, and the immediate-publish side effect. The one gap is the undocumented 'direction' parameter, which an agent would have to guess at.

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 only 25% (only 'website' is documented), so the description must compensate. It does add meaning for 'palette' (slugs sourced from website_publish_status 'palettes' / 'premium.choices') and implies the 'style' enum values, but 'direction' is never mentioned and remains entirely opaque.

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: 'Switch an existing site between the standard and the premium design, or to another palette.' An agent can tell this changes an existing site's design rather than creating a page or switching a template. It stops short of naming the nearest sibling (website_switch_template) to draw the line explicitly.

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?

Gives a concrete condition (premium requires a paid plan; free workspaces get 'blocked' with 'upsell') and states the prerequisite flow. It also routes the agent to confirm_action by explaining that the call returns status='confirmation_required' with an action_id and plan_token. It does not contrast this with alternative style/template tools, so the guidance is clear but not exhaustive.

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