AI virtual staging that doesn't change the house.
Scored across 3 tools
stage_room is clearly distinct as the job-starting action, while get_staging_result and get_verification both retrieve information for a staged job. Their boundary is mostly clarified by the descriptions: one returns status plus a summary, the other returns full verification evidence, though an agent may still briefly hesitate between them.
The names are readable and mostly follow a verb_noun pattern: get_staging_result, get_verification, and stage_room. The mix of get_ retrieval tools with an action-oriented stage_room tool is a minor deviation rather than an inconsistency.
Three tools are well-scoped for a staging-and-verification workflow: start the job, collect the staged result and summary, and fetch detailed verification evidence. Each tool has a clear role, and there are no obviously redundant tools.
The surface covers the core lifecycle: create a staging job, poll its result, and retrieve detailed RELTOLock verification evidence. Minor operational gaps such as canceling a job or listing past jobs are not present, but they are not essential to the stated workflow.
Check a RELTO staging job by jobId and, when it is done, get the staged photo URL, the link to the original photo, and the RELTOLock™ verification summary (state, how many elements were measured, and any element lines that came back altered or inconclusive). RELTOLock™ verifies RELTO's own staged outputs against the original photo, window by window and door by door; the verification mark is withheld if anything moved. It does not scan or verify photos staged by other tools. If the job is still queued or processing, call again in a few seconds.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | The jobId returned by stage_room. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
No annotations are present, so the description must carry the behavioral load, and it does: it discloses the asynchronous/polling model, that the verification mark is conditionally withheld when elements moved, and what the summary contains (state, element count, altered/inconclusive lines). It does not cover failure/error states (e.g., a failed job) or permission needs, which keeps it below 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?
Purpose and return payload are front-loaded in the first sentence, and the polling instruction closes usefully. The middle explanation of RELTOLock™ ('window by window and door by door') is somewhat promotional and could be trimmed without losing agent-relevant 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?
With no output schema and no annotations, the description correctly compensates by enumerating the returned fields and the conditional verification mark. Only the behavior on a failed or expired job is left unspecified.
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 single parameter is fully documented in the schema, including provenance ('The jobId returned by stage_room'), so the description adds no meaning beyond it. Baseline 3 applies for 100% schema coverage on a one-param 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?
States a specific verb and resource ('Check a RELTO staging job by jobId') and enumerates exactly what comes back: staged photo URL, original photo link, and RELTOLock™ verification summary. The clause 'It does not scan or verify photos staged by other tools' separates it from the get_verification sibling.
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 explicit polling behavior ('If the job is still queued or processing, call again in a few seconds') and a clear scope exclusion for other tools' staged photos. It stops short of naming get_verification as the alternative for those cases, so the routing is implied rather than spelled out.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Fetch the full RELTOLock™ verification evidence recorded for a finished RELTO staging job: the structural checks run against the original photo and their outcomes. Use this when the summary from get_staging_result is not enough, for example to show exactly which windows and doors were measured and what each check found. RELTOLock™ verifies RELTO's own staged outputs against the original photo, window by window and door by door; the verification mark is withheld if anything moved. It does not scan or verify photos staged by other tools.
| Name | Required | Description | Default |
|---|---|---|---|
| jobId | Yes | The jobId returned by stage_room. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full behavioral burden and does well: it explains that verification is performed against the original photo per window and door, and that the verification mark is withheld if anything moved. It does not address what happens when the job is unfinished, whether results are immutable, or any auth/size considerations, so it stops 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?
Front-loaded with the resource and effect, then usage routing, then scope boundary — good ordering. The third sentence partially restates the verification mechanism ('window by window and door by door' repeats the earlier clause), which costs a little density but also serves as scope framing.
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?
No output schema exists, and the description compensates by outlining what the evidence contains (structural checks run against the original photo, which windows/doors were measured, what each check found). Missing only edge-case behavior, such as what is returned for a job that has not finished verification.
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 the baseline is 3; the description adds that the jobId must reference a *finished* staging job, which narrows the acceptable values beyond the schema's 'jobId returned by stage_room'. Only a single parameter, so no further semantic load is needed.
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: fetching RELTOLock™ verification evidence (structural checks and outcomes) for a finished RELTO staging job. It is clearly distinguished from get_staging_result ('the summary ... is not enough') and from generic photo verification ('does not scan or verify photos staged by other tools').
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 names the trigger condition (when the summary from get_staging_result is not enough) and a concrete example use case (showing which windows and doors were measured and what each check found). It also names an exclusion — photos staged by other tools are not covered.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Start a RELTO staging job for one empty room photo. RELTO furnishes the room and runs RELTOLock™ verification on its own output before delivering it. RELTOLock™ verifies RELTO's own staged outputs against the original photo, window by window and door by door; the verification mark is withheld if anything moved. It does not scan or verify photos staged by other tools. Returns immediately with a jobId and status "queued"; rendering takes about a minute. Then call get_staging_result with the jobId to collect the staged photo and its verification summary.
| Name | Required | Description | Default |
|---|---|---|---|
| image | Yes | The empty room photo: a base64 string, a data URL (data:image/...;base64,...), or a public https URL. | |
| style | No | Staging style, for example "Modern Minimalist" (the default) or "Scandinavian". | |
| roomType | No | Room type, for example "living-room" (the default), "bedroom", or "kitchen". | |
| idempotencyKey | No | Optional key so a retried call returns the same job instead of creating a duplicate. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden and does so: it discloses asynchronous behavior ('returns immediately with a jobId and status queued'), expected latency ('about a minute'), and what RELTOLock does to its own outputs, including that the verification mark is withheld if anything moved. These are exactly the traits an agent needs before invoking a long-running job tool.
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?
Opens with the action and scope, then async/verification behavior, then the follow-up step — well front-loaded with no filler. The RELTOLock verification behaviour is described twice in slightly different words, which is mild redundancy but not harmful.
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?
No output schema exists, so the description supplies the return contract itself (jobId and 'queued' status), the latency expectation, and the follow-up tool call plus what that call returns. That is complete for a 4-parameter async job-creation tool.
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% (image formats, style default, roomType default, idempotencyKey purpose), so the schema already documents all four parameters. The description adds only the high-level constraint of 'one empty room photo' and no format or syntax detail beyond the schema, 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?
States a specific verb and resource ('Start a RELTO staging job for one empty room photo') and bounds the input scope to a single empty room photo. It also distinguishes itself from non-sibling tools by noting it 'does not scan or verify photos staged by other tools', so the agent can tell what this tool is and is not.
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 usage context: one empty room photo in, then 'call get_staging_result with the jobId' to collect output, and explicitly excludes photos staged by other tools. It stops short of naming get_verification or spelling out when-not conditions, but the primary routing instruction is explicit.
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.
get_staging_resultget_verificationstage_roomAI virtual staging for real estate — stage rooms, beautify floor plans, classify images.
AI virtual staging and architectural rendering: stage rooms, render interiors, exteriors, sketches.
Every visual AI tool for property listings — staging, enhancement, decluttering, cinematic video.
Enhance, virtually stage and turn real estate listing photos into video with AI.
Add one secure layer between your agents and this server.
