Explore Roomvana room types and styles, then open a link to redesign a room from a photo.
Scored across 3 tools
Each tool has a clearly distinct role: one action tool (design_a_room) and two parameter-lookup tools, with the list tools explicitly pointing back to the action tool's inputs. There is no realistic way to confuse them.
All names are snake_case and readable, with the two list tools sharing a consistent 'list_x' pattern. 'design_a_room' breaks the pattern slightly by inserting the article 'a', but the verb_noun intent is still obvious.
Three tools is on the lean side, but each earns its place: one generation action plus the two catalogue lookups needed to supply its parameters. The scope is inherently narrow since the actual redesign happens in an external studio link.
The surface cleanly covers the described workflow—discover valid styles, discover valid rooms, generate a pre-filled studio link. The only minor gap is the absence of any way to check a link's status or retrieve the finished design, though that may be intentionally delegated to the external studio.
Turn a room + style choice into a Roomvana studio link with those options pre-selected. The user opens the link, uploads a photo of the room, and gets an AI redesign in about 30 seconds. Validates the room and style against Roomvana's catalogue.
| Name | Required | Description | Default |
|---|---|---|---|
| room | Yes | Room or space id, e.g. 'bedroom', 'kitchen', 'backyard'. See list_room_types. | |
| notes | No | Optional free-text notes about the desired look (echoed back; not encoded in the link). | |
| style | No | Optional design style id, e.g. 'japandi', 'modern'. See list_design_styles. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does well: it discloses that the tool itself does not perform the redesign but returns a link, that the upload/redesign happens later in the studio (~30 seconds), and that inputs are validated against the catalogue. It does not cover failure behavior or rate/invocation concerns, but the out-of-band nature of the actual redesign is valuable context.
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 core action, and each sentence contributes (action, user flow, validation). Sizing is appropriate for the tool's complexity with no 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 annotations and no output schema, the description needs to explain the return value, and it does: a studio link with options pre-selected. Combined with the validation and timing details, an agent has enough to call it correctly, though failure/error handling is left unstated.
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 100%, so all three parameters are already documented in the schema. The description adds only a passing reference to 'room + style' validation and does not mention the notes parameter or the id formats beyond what the schema states, so the baseline 3 is appropriate.
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 concrete verb and resource: it turns a room+style choice into a Roomvana studio link with those options pre-selected. This clearly marks it as the action/generation tool versus the sibling list_room_types and list_design_styles, which it references only indirectly via 'catalogue'.
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?
The description implies the workflow (pick room + style, get a link where the user uploads a photo) and says it validates against the catalogue, which hints the list tools are prerequisites. However, it never explicitly states when to use this versus alternatives or what happens on invalid room/style input.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
List the interior-design styles Roomvana can render (e.g. modern, japandi, industrial), each with a short description. Use this to pick a style for design_a_room.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the burden, but the tool is a zero-parameter read-only enumeration so the risk surface is minimal. It discloses the return shape (each style plus a short description), though it says nothing about ordering, size, or whether results are cached/static.
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 tight sentences: the first says what comes back, the second says what to do with it. No filler and the purpose is front-loaded.
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 parameterless lister with no output schema, the description supplies everything needed: the enumerated domain, the shape of each item, and the follow-up action. Nothing an agent needs in order to call 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?
The tool takes no parameters, so the schema is trivially complete and the description needs to say nothing further about inputs. Baseline 4 applies for a 0-parameter tool.
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?
Specific verb (List) plus resource (interior-design styles) with concrete examples of the values returned. It is also distinguishable from the sibling list_room_types, which enumerates a different domain.
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 this to pick a `style` for design_a_room" gives clear usage context and names the downstream consumer, which is exactly the agent's decision point. No explicit when-not or exclusion is stated, which keeps it 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.
List the room and outdoor space types Roomvana can redesign (interior rooms, house exterior, and garden/outdoor spaces). Use this to pick a room for design_a_room.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are provided, so the description carries the burden. 'List' implies a non-mutating read, and the enumerated categories give a rough sense of the returned content, but there is no disclosure of return shape, ordering, or any auth/limit characteristics. Adequate for a zero-param read tool, but thin.
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 short sentences with zero filler, and the scoping/usage instruction is front-loaded after the purpose statement. Every clause earns its place.
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 list with no output schema, the description covers what the tool returns in broad categorical terms and why to call it. It could say more about the actual returned identifiers/values an agent would pass to design_a_room, but nothing essential 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?
The tool takes zero parameters, so the baseline of 4 applies. The description references a `room` value that the tool's output feeds into, which is a helpful hint, but there are no parameters whose semantics need explaining.
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 ('List the room and outdoor space types') and enumerates the categories returned (interior rooms, house exterior, garden/outdoor). It also binds itself to the downstream sibling design_a_room, so an agent can distinguish it from list_design_styles without opening 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?
Explicitly states when to use it: 'Use this to pick a `room` for design_a_room.' That is a clear contextual trigger. It does not name an alternative or a when-not condition (e.g., list_design_styles for styles), 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.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
design_a_roomlist_design_styleslist_room_typesAI virtual staging for real estate — stage rooms, beautify floor plans, classify images.
A design-style library for AI agents: search real styles, fetch a ready-to-apply design spec.
Search curated design styles, real product screens, and user flows for evidence-based design work.
Every visual AI tool for property listings — staging, enhancement, decluttering, cinematic video.
Add one secure layer between your agents and this server.
