Skip to main content
Glama

Create a preview link

r3_preview_create
DestructiveIdempotent

Create a shareable preview link for a saved R3 project, so a person can open it in a browser and see it running. The link is valid for 7 days and does NOT make the project public; making a new one is free. It is how the user sees what you built. Takes the projectId returned by r3_project_create. Where the client shows MCP Apps (Claude on the web, desktop and mobile), the preview also shows as a playable card right in the chat, under this answer: use it when the user asks to see or play the project here or in the chat. When an R3 tab has the project open, the project's picture (its card and the link's image) is refreshed from that tab; when none has, the picture refreshes the next time the project is opened in R3.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "projectId": "<projectId>"
    },
    "name": "r3_preview_create"
  }
}

Input Schema

NameRequiredDescriptionDefault
projectIdYesThe project id, as returned by r3_project_create.

Output Schema

NameRequiredDescriptionDefault
cardNo
slugYes
answerYesThis answer in words: what was done, what R3 measured, decided or refused, and what to do next. The same text as the result's text block. Read it: the fields beside it are the data, this is the guidance.
projectIdYes
previewUrlYes
environmentYes
cameraControlsYes
expiresInHoursYes
pictureOutdatedYes
pictureRefreshedYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedOutput schema / properties / card
      Added value: +{
      +  "additionalProperties": false,
      +  "properties": {
      +    "apiOrigin": {
      +      "type": "string"
      +    },
      +    "createdAt": {
      +      "type": "string"
      +    },
      +    "environment": {
      +      "type": "string"
      +    },
      +    "expiresAt": {
      +      "type": "string"
      +    },
      +    "liveOrigin": {
      +      "type": "string"
      +    },
      +    "pictureUrl": {
      +      "type": [
      +        "string",
      +        "null"
      +      ]
      +    },
      +    "previewUrl": {
      +      "type": "string"
      +    },
      +    "projectId": {
      +      "type": "string"
      +    },
      +    "projectName": {
      +      "type": "string"
      +    },
      +    "seq": {
      +      "maximum": 9007199254740991,
      +      "minimum": -9007199254740991,
      +      "type": "integer"
      +    },
      +    "slug": {
      +      "type": "string"
      +    },
      +    "token": {
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "projectId",
      +    "projectName",
      +    "previewUrl",
      +    "slug",
      +    "token",
      +    "expiresAt",
      +    "pictureUrl",
      +    "createdAt",
      +    "seq",
      +    "environment",
      +    "liveOrigin",
      +    "apiOrigin"
      +  ],
      +  "type": "object"
      +}
  2. Changed2 schema fields changed
    • addedOutput schema / properties / cameraControls
      Added value: +{
      +  "type": [
      +    "boolean",
      +    "null"
      +  ]
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "projectId",
      -  "previewUrl",
      -  "slug",
      -  "expiresInHours",
      -  "environment",
      -  "pictureRefreshed",
      -  "pictureOutdated",
      -  "answer"
      -]New value: +[
      +  "projectId",
      +  "previewUrl",
      +  "slug",
      +  "expiresInHours",
      +  "environment",
      +  "pictureRefreshed",
      +  "pictureOutdated",
      +  "cameraControls",
      +  "answer"
      +]
  3. Changed2 schema fields changed
    • addedOutput schema / properties / pictureOutdated
      Added value: +{
      +  "type": "boolean"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "projectId",
      -  "previewUrl",
      -  "slug",
      -  "expiresInHours",
      -  "environment",
      -  "pictureRefreshed",
      -  "answer"
      -]New value: +[
      +  "projectId",
      +  "previewUrl",
      +  "slug",
      +  "expiresInHours",
      +  "environment",
      +  "pictureRefreshed",
      +  "pictureOutdated",
      +  "answer"
      +]
  4. Changed2 schema fields changed
    • addedOutput schema / properties / pictureRefreshed
      Added value: +{
      +  "type": "boolean"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "projectId",
      -  "previewUrl",
      -  "slug",
      -  "expiresInHours",
      -  "environment",
      -  "answer"
      -]New value: +[
      +  "projectId",
      +  "previewUrl",
      +  "slug",
      +  "expiresInHours",
      +  "environment",
      +  "pictureRefreshed",
      +  "answer"
      +]
  5. Changed2 schema fields changed
    • addedOutput schema / properties / answer
      Added value: +{
      +  "description": "This answer in words: what was done, what R3 measured, decided or refused, and what to do next. The same text as the result's text block. Read it: the fields beside it are the data, this is the guidance.",
      +  "type": "string"
      +}
    • changedOutput schema / required
      Previous value: -[
      -  "projectId",
      -  "previewUrl",
      -  "slug",
      -  "expiresInHours",
      -  "environment"
      -]New value: +[
      +  "projectId",
      +  "previewUrl",
      +  "slug",
      +  "expiresInHours",
      +  "environment",
      +  "answer"
      +]
  6. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Beyond the annotations, the description discloses several non-obvious traits: 7-day link lifetime, no public exposure, no cost, a playable card rendered inline on MCP Apps clients, and the conditional image-refresh behavior depending on whether an R3 tab has the project open. Given destructiveHint=true and openWorldHint=true, the main residual gap is that it never states what an existing preview link or image is replaced/invalidated by when a new one is created; 'making a new one is free' partially softens rather than explains the destructive aspect.

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?

Core purpose, lifetime, and privacy posture are front-loaded in the first two sentences, and the client-specific card behavior follows logically. The final sentence about card/image refresh is dense and somewhat tangential, but it is the only place that behavioral nuance is documented, so it still earns its space.

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

Completeness4/5

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

With only one required parameter and an output schema handling return values, the description covers everything an agent needs to select and invoke the tool: what it produces, how long it lasts, which id to pass, and client-dependent rendering. The only meaningful omission is what happens to a pre-existing link or image when a new preview is generated.

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?

There is a single parameter at 100% schema coverage, and the schema already documents projectId as coming from r3_project_create; the description repeats that sourcing without adding format or validation detail. Baseline 3 applies because the schema does the work and the description contributes only a minor provenance reminder.

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 first sentence names a specific verb (create) and resource (a shareable preview link for a saved R3 project) plus the observable outcome: a person can open it in a browser and see it running. It distinguishes itself from adjacent tools like r3_editor_set_preview_image and r3_preview_remove by framing the link as the user-facing artifact, and explicitly states the 7-day lifetime and that it does NOT publish the project.

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?

It gives a concrete use condition: 'use it when the user asks to see or play the project here or in the chat', and frames the tool as 'how the user sees what you built'. It also ties input to r3_project_create, implying it is a post-creation step. It does not state when NOT to use it or name an alternative such as r3_editor_set_preview_image for in-editor images, so it stops short of a full when/when-not/alternative statement.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources