CueFrame

Score Composition

score_composition

Idempotent

Queue the durable server-side judge — it snapshots the exact authored target, samples eval beats, captures frames asynchronously, and grades editorial/spatial/brand/caption. Then wait_job(kind="verify", id=jobId) for per-criterion scores, weighted composite, worst-first critique, and checkpointId. body.composition is optional (absent ⇒ ACTIVE). Fix the lowest criterion via apply_composition and re-score. Idempotent per immutable snapshot; compose_verify bills only on the guarded success terminal.

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": "score_composition"
  }
}

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.

Changed5 schema fields changedOct 28, 2026
- addedInput schema / $defs
```
Added value: +{
+  "__schema0": {
+    "maxLength": 128,
+    "minLength": 1,
+    "type": "string"
+  }
+}
```
- addedInput schema / properties / commandId / $ref
```
Added value: +"#/$defs/__schema0"
```
- 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: +{
+  "editorialIntent": "punchy, founder-led"
+}
```
First observedOct 10, 2026

TDQS

A4.3/5.0

Behavior5/5

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

Annotations already declare non-read-only, idempotent, non-destructive, closed-world; the description adds real value beyond them by explaining the async job model, idempotency keyed to the immutable snapshot, and the billing rule (compose_verify bills only on the guarded success terminal). It also warns that a stale/foreign compositionId is a 404, not a silent fallthrough.

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 core action and the follow-up call, then the optional-target rule and remediation loop. Dense with product jargon ("guarded success terminal", "eval beats") but every sentence carries operational information; no filler.

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?

Output schema exists, so return values needn't be spelled out, yet the description still previews what wait_job yields (per-criterion scores, weighted composite, worst-first critique, checkpointId). That covers the async mutation workflow well; minor gaps remain on failure modes other than the 404 case.

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 description's main param claim (body.composition absent ⇒ ACTIVE) merely restates the schema's own description. It adds no meaning for commandId retry identity or the interplay of session_id/compositionId beyond what the schema already says, so 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?

Names a specific verb+resource: queues a durable server-side judge that snapshots the authored target, samples eval beats, captures frames asynchronously, and grades editorial/spatial/brand/caption. This is clearly distinguishable from compose, create_render, and validate_composition in the sibling list.

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?

Explicitly describes the follow-up flow (wait_job(kind="verify", id=jobId) for scores), the optional-target rule (body.composition absent ⇒ ACTIVE), and the remediation loop (fix lowest criterion via apply_composition and re-score). It does not, however, contrast itself against near siblings like validate_composition or compose, leaving that inference to the agent.

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.