Make a website with 8B from chat: live animated preview, edits in plain words, HTML download
Scored across 3 tools
Each tool targets a distinct stage: explore_designs lists available designs, get_design_brief retrieves the detailed specification for a chosen design, and generate_site creates or updates the site. The descriptions clearly delineate their roles, leaving no room for confusion.
All tool names follow a consistent verb_noun pattern in snake_case: explore_designs, get_design_brief, generate_site. The minor plural/singular difference in nouns is negligible and does not break the predictable convention.
Three tools form a tight, well-scoped pipeline for building a site: explore designs, get the brief, generate the site. Each tool is essential and earns its place; the count is minimal but sufficient for the focused purpose.
The surface covers the full build workflow: selecting a design, obtaining the required content fields, and generating or updating the site. The ability to update via base_preview_id and the return of preview and download links complete the lifecycle with no obvious gaps.
Lists 8B site designs: the look, the structure and the kinds of business each one suits. Use it to choose the design for the user's site.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and openWorldHint=false, so the safety profile is covered structurally. The description adds useful context that the result is a descriptive catalog (look/structure/business fit), but says nothing about ordering, count, or how designs are identified.
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?
Two sentences, no filler, and the resource plus its contents are front-loaded ahead of the usage hint. Every clause carries information.
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?
For a zero-param, read-only, no-output-schema tool, the description covers purpose, content, and intended use. It would be complete at 5 if it distinguished itself from get_design_brief, the sibling an agent is most likely to reach for instead.
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?
The tool takes zero parameters, so there is no parameter semantics to explain; baseline 4 applies. The description correctly presents it as an unfiltered enumeration rather than implying hidden arguments.
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 ('Lists') and resource ('8B site designs') and even characterizes the content of each design — look, structure, business fit. It stops short of naming or contrasting the siblings generate_site and get_design_brief, so 5 is not earned.
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?
'Use it to choose the design for the user's site' gives an implied trigger, but there is no explicit when-not guidance and no mention of how this differs from get_design_brief, which is the most likely confusable sibling.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Generates the user's site with 8B from a design and the texts, colors, fonts and photo queries written for the business, and shows a live, animated preview in the conversation. Call get_design_brief first to see the fields. Returns the preview id, the preview link and the link to download the site. To change a site that is already built (a color, some texts, a photo), call it with base_preview_id and only the values that change: everything else is kept.
| Name | Required | Description | Default |
|---|---|---|---|
| fonts | No | Current font family → new Google Fonts family spec | |
| texts | No | New text per field id from get_design_brief | |
| colors | No | New CSS color per palette id | |
| images | No | Image id → {query: English Unsplash search query, alt: photo description in the site language}. Photos of the same kind share one query; each place gets a different photo | |
| language | No | Language of the site, e.g. "ru" or "de", the same as for get_design_brief. Not needed with base_preview_id | |
| design_id | No | Design id from explore_designs. Required for a new site, not needed with base_preview_id | |
| site_name | No | Name of the business or project the site is for. Required for a new site | |
| base_preview_id | No | To change an existing preview: its id. Send only the values that change; the rest is taken from that preview |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false, idempotentHint=false and openWorldHint=true, so the safety profile is covered. The description adds real value beyond them: the live animated preview shown in the conversation, the exact return values, and the partial-update semantics ('everything else is kept'). It does not mention latency or failure modes of an open-world generation call.
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, front-loaded with the primary action and return values, then the prerequisite, then the update mode. Dense but every sentence carries actionable information; the middle return-values sentence could arguably be tighter.
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 explicitly enumerates the return payload (preview id, preview link, download link), covers the zero-required-parameter create vs. update branching, and points to the sibling needed to fill nested object keys. Nothing an agent needs to invoke it correctly is missing.
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 all eight parameters including the conditional requirements on language and design_id. The description reinforces the update contract with base_preview_id but adds no syntax or format detail the schema lacks, so the baseline of 3 applies.
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 verb (generates) and resource (the user's site) plus the model (8B) and the inputs it consumes (design, texts, colors, fonts, photo queries). It also distinguishes itself from the siblings by requiring get_design_brief and explore_designs outputs as inputs.
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 states explicit prerequisites ('Call get_design_brief first to see the fields') and gives a clear when-to-use branch for the modify case, naming base_preview_id as the alternative path and specifying that only changed values need to be sent.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns the brief for writing the site in a design: every text with a hint and max length, the color palette, fonts and photos. Write them for the user's business and pass the values to generate_site.
| Name | Required | Description | Default |
|---|---|---|---|
| language | No | Language of the site you are making, e.g. "ru" or "en": the word limits are adjusted to it | |
| design_id | Yes | Design id from explore_designs |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true, destructiveHint=false and closed-world, so safety is covered. With no output schema, the description usefully discloses the return payload's contents (texts with hints and max lengths, palette, fonts, photos), which is the key behavioral detail an agent needs. It does not describe the response structure or size, keeping it short of a 5.
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?
Two sentences, front-loaded with what is returned, then the follow-up action. No filler, and every sentence carries information an agent can act on.
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 and only two parameters, the description covers what the brief contains and what to do with it, which is close to sufficient. It could add a note on whether the returned texts are templates to be rewritten versus fixed content, which would fully close the loop.
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%: design_id's provenance from explore_designs and language's effect on word limits are both documented in the schema. The description adds no format or syntax detail beyond that, so the baseline 3 applies.
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 (returns the design brief) and enumerates its contents: texts with hints and max lengths, color palette, fonts, photos. It also names the downstream consumer, generate_site, which separates it from siblings before the agent opens either schema.
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 clear workflow context — write the returned texts for the user's business, then pass the values to generate_site — and the schema ties design_id to explore_designs. However, it never states when not to use this tool or what an alternative would be.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
explore_designsgenerate_siteget_design_briefBuild, edit, and publish real websites and online stores by chatting with your AI assistant.
Build, version, review, and export websites, web apps, and games from a conversation.
Create or redesign websites and build web apps by chatting. Preview, refine, and publish in Revamp.
Build a real 3D website by chatting: pages, models and text in space, published to a live URL.
Add one secure layer between your agents and this server.
