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

Annotations already declare the call read-only and non-destructive, so safety is covered. The description adds real behavioral context beyond that: the result appears as an interactive card, shows the latest draft by default, and switching live shows the published version – useful framing the annotations do not convey.

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 usage trigger, followed by behavior and parameter hints. Every sentence carries information; it is slightly chatty with the quoted example but not wasteful.

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?

An output schema exists, so return values need not be explained. For a 3-param read-only tool the description covers purpose, trigger, default behavior, the live override, and the site_id flexibility, leaving little an agent needs to infer.

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 67%; live and path are already documented in the schema. The description compensates by documenting the undocumented site_id, noting it can be the site's name, and reinforces the live/draft distinction. This meaningfully adds to what the schema provides.

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: show a preview of one of the user's sites or a page. It further distinguishes itself from a plain fetch by describing the interactive card behavior ("click things to change them"), though it never names siblings like screenshot-site or get-site 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 clear triggering context ("when the user wants to see or look at one of their WebTwizz sites") plus an example utterance ("show me my bakery site") and the after-a-change scenario. It lacks an explicit when-not or a named alternative, so it falls short of a 5.

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