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

Annotations already cover the read-only and non-destructive profile, yet the description still adds real behavior: it flags that a published site may have edits that are NOT live, and that connected external sites/shops are included in the result with a warning never to answer 'no site' when one is listed. Those are non-obvious gotchas an agent could not derive from annotations or schema, and the read-only scope limit on publishing is stated explicitly.

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?

The content is front-loaded — the returned field list comes first, then the drill-down behavior, then the connected-sites caveat — and nearly every clause carries information. It is dense and em-dash-heavy, and the enumeration is long, but no sentence is filler.

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 does the heavy lifting by effectively describing the return payload and adding the connected_sites caveat, which is enough for an agent to answer status questions correctly. The one gap is the undocumented `limit` parameter and any pagination behavior for long page lists.

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 50%: the `site` parameter is documented in the schema and reinforced by the description ('Pass a site name to get its pages'), but `limit` is undocumented in both places, leaving its role as a page-list cap to inference. The description adds useful behavioral meaning for `site` but does not compensate for the unexplained parameter.

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?

The description names a specific resource (the workspace's websites) and enumerates exactly what status information is returned: name, type, languages, draft/published state, publish date, address, page count, and the unpublished-edits flag. The phrase 'the part the status field does not tell you' explicitly distinguishes it from a plain publish-state check, which is what separates it from siblings like website_publish_status.

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?

It gives concrete when-to-use triggers ('is the site published', 'did my change go live', 'how many pages does it have') and states the call pattern for the per-site drill-down ('Pass a site name to get its pages'). It also closes off a likely wrong path by saying publishing an existing site is not available over MCP, though it never names a sibling tool as an alternative.

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