Skip to main content
Glama

WebZum - The Hosting Layer for AI-Generated Web Content

by io.github.suprraz

update_site_html

Edit a generated WebZum site by describing the change in natural language.

This is the primary editor tool. Given a user instruction (in conversationHistory), the WebZum editor builds the minimal site tree, sends it to an LLM with the user's verbatim words, applies the returned HTML diff across every page that contains each affected section, and reassembles into a new version.

Use this for nearly all edits: "make the hero say X", "remove the testimonials section", "change the about-us copy to be friendlier", "swap the order of the sections on the home page".

Required: businessId, versionId, and a conversationHistory containing at least one user turn. The LLM reads the user's verbatim words — do not paraphrase.

Returns { versionId, status: 'completed' | 'in_progress', ...extra }. If status is 'in_progress', the edit is still running in the background — poll get_site_status with the returned versionId every 5-10s until isComplete is true.

Concurrency: edits on the same businessId MUST be serial. Never fire parallel edit calls on the same site; concurrent edits race and may return the wrong versionId. Wait for each edit to complete (status: 'completed' OR isComplete on get_site_status) before issuing the next one.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
versionIdYesThe versionId to base this edit on.
businessIdYesThe site's businessId.
conversationHistoryYesRecent chat turns that produced this edit request. Must include at least one user turn. Pass the user's verbatim words so the editor LLM can read them directly.

Schema Changelog

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

  1. Added

TDQS

A4.5/5.0
Behavior5/5

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

Goes far beyond the minimal annotations (readOnlyHint false, destructiveHint false) by disclosing the internal process: builds minimal site tree, sends to LLM, applies HTML diff across pages, reassembles. Also explains async status 'in_progress' with polling guidance, and warns about concurrency races returning wrong versionId. This is exceptionally transparent.

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

Conciseness5/5

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

Although about 200 words, every sentence earns its place: purpose, process examples, required params, return behavior, polling, and concurrency warning. It is well-structured and information-dense without fluff.

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 there is no output schema, the description fully explains the return object and async polling behavior. It also covers critical concurrency constraints and parameter prerequisites, making the tool fully actionable for an agent.

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?

The input schema already has 100% coverage with descriptions for all three parameters. The description restates the requirement for conversationHistory (at least one user turn, verbatim words) and explains the process, but adds little new parameter-level semantic detail beyond the schema.

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?

The description clearly states the tool's purpose: 'Edit a generated WebZum site by describing the change in natural language.' It calls itself the 'primary editor tool' and provides specific examples (e.g., 'make the hero say X', 'remove the testimonials section'), distinguishing it from more specialized sibling tools like regenerate_footer.

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

Usage Guidelines4/5

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

Explicitly directs usage: 'Use this for nearly all edits' with concrete examples, plus required parameters and concurrency constraints. However, it does not enumerate when-not-to-use or name alternative tools explicitly, only implying exceptions through 'nearly all.'

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

All WebZum - The Hosting Layer for AI-Generated Web Content toolsInspect
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

A4/5.0
Disambiguation4/5

Most tools have clear, distinct purposes: cloning, creating, hosting, editing, and regenerating different site parts. The main ambiguity is between create_lead_gen_site and generate_geo_page, which both create lead-gen pages but differ in targeting and workflow; however, their descriptions clarify the use cases sufficiently.

Naming Consistency4/5

Tool names follow a consistent lowercase verb_noun pattern (e.g., clone_site, host_file, update_site_html). Minor inconsistencies exist: create vs. generate for similar actions (create_site vs. generate_geo_page) and get vs. list for retrieval (get_hosted_files vs. list_user_sites), but these are predictable and readable.

Tool Count3/5

With 17 tools, the count is slightly heavy for a hosting service, but the variety of operations (creation, cloning, file hosting, editing, regeneration, status, search) justifies most of them. A few tools (e.g., four regenerate_* tools) could potentially be consolidated, but the scope still feels reasonable.

Completeness4/5

The toolset covers the full lifecycle: create, clone, host, list, edit, update, and regenerate site components. Notable gaps include no delete operation for sites or files and no explicit version rollback, but agents can work around these by using host_file to overwrite and relying on site status for progress.

Resources