CueFrame

Preview Frame

preview_frame

Read-onlyIdempotent

Queue durable still-frame evidence for layout/copy judgment. Returns immediately with {jobId, kind:'preview_frame', status}; then call wait_job(kind="preview_frame", id=jobId) for artifact metadata and up to four embedded frame images; fetch failures or payload limits may return fewer. Use wait_job imageIndices to read other original image artifacts from the completed job, at most four indices per call, without rendering again. Repeating the same arguments repeats the same selection. Artifact URLs alone are not observed pixels. The immutable snapshot records geometry, layers, warnings, and whether the target was persisted, inline, or session scratch. A still cannot prove motion — use preview_clip or preview_component for animation.

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>",
      "body": "<body>"
    },
    "name": "preview_frame"
  }
}

Input Schema

Name	Required	Description
`body`	Yes
`commandId`	No	Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.
`projectId`	Yes	projectId (path).

Output Schema

Name	Required	Description
`kind`	No	Job family, e.g. `verify` \| `preview` \| `brand_kit_extract`.
`jobId`	No	Poll GET /v1/jobs/{jobId} / wait_job until terminal.
`jobKey`	No	Deterministic identity of the work (content hash of every input the result depends on). Re-enqueueing the same key returns the same job while it runs; a failed key revives as a fresh attempt.
`status`	No	running on a fresh/deduped enqueue; succeeded when an identical request already completed. Cancelled is part of the shared status vocabulary; identical cancelled work revives to running.

Schema Changelog

Changes observed during successful MCP inspections.

Changed7 schema fields changedOct 28, 2026
- addedInput schema / $defs
```
Added value: +{
+  "__schema0": {
+    "type": "number"
+  },
+  "__schema1": {
+    "maxLength": 128,
+    "minLength": 1,
+    "type": "string"
+  }
+}
```
- addedInput schema / properties / body / properties / timestamps / items / $ref
```
Added value: +"#/$defs/__schema0"
```
- removedInput schema / properties / body / properties / timestamps / items / type
```
Removed value: -"number"
```
- addedInput schema / properties / commandId / $ref
```
Added value: +"#/$defs/__schema1"
```
- removedInput schema / properties / commandId / maxLength
```
Removed value: -128
```
- removedInput schema / properties / commandId / minLength
```
Removed value: -1
```
- removedInput schema / properties / commandId / type
```
Removed value: -"string"
```

Changed1 schema field changedOct 22, 2026

addedInput schema / properties / commandId

Added value: +{
+  "description": "Retry identity. A call repeated with the same commandId returns the first result instead of acting twice.",
+  "maxLength": 128,
+  "minLength": 1,
+  "type": "string"
+}

Changed1 schema field changedOct 18, 2026

addedInput schema / properties / body / example

Added value: +{
+  "imageFormat": "jpeg",
+  "timestamps": [
+    1.5,
+    4
+  ]
+}

First observedOct 10, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Goes well past the readOnly/idempotent hints: discloses the async job contract (immediate {jobId, kind, status} return), the follow-up call needed, a cap of four embedded images, partial results on fetch failure or payload limits, cache behavior on repeated args, and that URLs are not observed pixels. These are exactly the traits annotations cannot express.

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?

Front-loaded with the immediate return contract before the follow-up instructions, and nearly every sentence carries unique operational information. It is dense and runs long, spanning wait_job usage and vision-token caveats, but no sentence is filler.

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?

For an async render tool with a nested body object and an output schema, the description supplies the missing pieces: the immediate-response shape, the job-polling path, image-count limits, and failure-mode expectations. An agent could invoke and complete this flow from the description alone.

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?

Schema coverage is 67% and the schema itself documents scale, session_id, timestamps, imageFormat, jpegQuality, and compositionId thoroughly. The description adds no parameter-level meaning for this tool — its numeric caps ('at most four indices per call', '18 per request' is only in the schema) refer to wait_job, not to preview_frame inputs. Baseline 3 applies.

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?

States a specific verb and resource ('queue durable still-frame evidence for layout/copy judgment') and implicitly scopes it to stills, which separates it from the motion siblings it names. An agent can tell what it does and what it produces without opening the schema.

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

Usage Guidelines5/5

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

Explicit routing: call wait_job(kind="preview_frame", id=jobId) to get artifacts, and an explicit when-not with the alternative named — 'A still cannot prove motion — use preview_clip or preview_component for animation.' This is the when/when-not/alternatives pattern in full.

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

All CueFrame tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.