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

Annotations already flag destructiveHint=true and openWorldHint=true, and the description adds non-obvious context beyond them: the work is delegated to the site's AI and shown live on the card, it consumes account credits, and 'each call starts another change' (non-idempotent, cumulative). It doesn't cover failure handling or whether confirmation is required for destructive edits.

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?

Three sentences, with the usage trigger front-loaded and no filler. The middle sentence is slightly redundant ('Sends the request to the site's WebTwizz AI, which edits the site, and shows the work live on the card') but still earns its place by explaining the async/live behavior.

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 an output schema present, return values need no explanation, and the description covers the key operational facts for a destructive, open-world, credit-consuming edit: delegation to site AI, live feedback, per-call credit use. Missing only edge cases like failure behavior or confirmation requirements.

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 the schema already documents site_id, request, files, images and reference_url in detail. The description adds 'in the user's words plus any detail from the conversation' for request, which is marginal beyond the schema's own wording. Baseline 3 is appropriate when the schema carries the parameter burden.

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 concrete verb and resource ('change one of their WebTwizz sites') and enumerates the kinds of changes covered (sections, pages, copy, design, features, fixes, question answers). It does not explicitly distinguish itself from close siblings such as update-site, edit-element, or edit-text, but the natural-language AI-request framing is distinctive enough to route an agent.

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?

Opens with an explicit trigger condition ('Use this when the user wants to change one of their WebTwizz sites...'), which is clear when-to-use guidance. It does not state when NOT to use it or name the overlapping alternatives (edit-element, edit-text, update-site), so an agent must infer the boundary.

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