Orivox AI Website Builder

create_new_site

Submit the complete one-shot HTML document for the project's HOMEPAGE.

Call create_project first and follow its build_instructions; pass the full document ( through ) as html in ONE call. Returns preview_url, auto_fixed, and needs_attention items to fix via apply_dom_ops.

ALSO how you REBUILD an existing homepage. The document replaces whatever index.html currently holds, so call this again with a full document to redesign it wholesale -- replace_page refuses index.html by design (422), and that refusal is not a dead end. Use apply_dom_ops for small edits and this for a rewrite; never try to reconstruct a redesign out of dozens of dom ops.

The document may include client-side app logic in blocks, wired via addEventListener (inline on*= handlers are stripped by the save sanitizer). Every visible control must actually work in the submitted document.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`html`	Yes
`project_guid`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

Changed3 schema fields changedAug 24, 2026

addedInput schema / properties / project_guid
```
Added value: +{
+  "type": "string"
+}
```
removedInput schema / properties / project_id
```
Removed value: -{
-  "type": "string"
-}
```

changedInput schema / required

Previous value: -[
-  "project_id",
-  "html"
-]New value: +[
+  "project_guid",
+  "html"
+]

First observedAug 4, 2026

TDQS

A4.6/5.0

Behavior5/5

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

No annotations are provided, so the description carries the full behavioral burden. It discloses that the document replaces whatever index.html currently holds, that inline on* handlers are stripped by the save sanitizer, that client-side logic via addEventListener is allowed, and that the response includes preview_url, auto_fixed, and needs_attention. This is rich, non-obvious behavioral information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is longer than average, but almost every sentence carries substantive guidance: payload format, tool ordering, rebuild semantics, alternative routing, and sanitizer constraints. It is front-loaded with the core action; minor awkward phrasing like 'ALSO how you REBUILD' and a slightly conversational tone keep it from a 5.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given no annotations and two required parameters, the description covers the input format, the prerequisite call, return values, the destructive replacement behavior, sanitizer rules, and the distinction from apply_dom_ops and replace_page. The only minor gap is not spelling out project_guid by name, but the explicit create_project-first instruction provides a sufficient source for it.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate. It does richly explain the html parameter: the full document from <!DOCTYPE html> through </html> in one call. However, it never explicitly names project_guid or says to pass the project returned by create_project; it only implies this via 'Call create_project first' and 'the project's HOMEPAGE'.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb ('Submit') and resource ('HOMEPAGE'), and adds the key scope constraint: it takes the complete one-shot HTML document. It is clearly differentiated from siblings because replace_page is said to refuse index.html while this tool is the designated replacement path for the homepage.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit usage sequencing: call create_project first and follow its build_instructions, then pass the full HTML in one call. It also states when NOT to use it ('use apply_dom_ops for small edits'), when to call it again (wholesale redesign), and why replace_page is not a valid alternative for index.html.

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

All Orivox AI Website Builder tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.8/5.0

Disambiguation4/5

Most tools pair a distinct action with a distinct resource and long descriptions make intent clear. Still, `search_domains` already provides exact-domain checks, overlapping with `check_domain`, and the `create_project` vs `create_new_site` vs `create_page` cluster takes careful reading.

Naming Consistency5/5

The vast majority are snake_case verb_noun: list_projects, create_project, delete_page, get_preview_url, write_asset, query_database, publish_website. The only visible outlier is whoami, but it is standard enough that it does not disrupt predictability.

Tool Count2/5

At 36 tools this is meaningfully heavier than the rubric's 'too many' threshold, even though the scope spans websites, backends, domains, gallery images, and databases. It makes selection harder and a sizeable portion of the surface is niche or lifecycle internal.

Completeness4/5

The core site lifecycle is well covered: project, htmlmanag, assets, preview/publish, validation, deletion, uploaded images, backend files/logs, database reading, domain search and purchase linking. Workable non-critical gaps exist, e.g. no separate project metadata rename and no direct way to delete database rows or a database outside of deleting the project.

Resources

Need Help?