GenFlick

Prepare the exact system quote and approval card now, without exploratory reads

native.genads_prepare_creative

DestructiveIdempotent

Prepare the exact system quote and approval card now, without exploratory reads. For a new video supply operationId and videoPlan {title, prompt}; native code links the saved brief, concept, variant and media with Seedance 2.0 Mini 480p, 9:16, 6s defaults. Include settings only for explicit creator choices, and referenceSourceIds only for known reviewed sources. For an existing creative or a still supply the complete brief/concept/variant/media revision-bound setup instead. Saves all records, quote and card atomically and ends this response. Starts no generation.

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": {
      "work_id": "<work_id>",
      "arguments": "<arguments>",
      "expected_catalog_version": "<expected_catalog_version>",
      "read_skills": "<read_skills>",
      "request_key": "<request_key>"
    },
    "name": "native.genads_prepare_creative"
  }
}

Input Schema

Name	Required	Description
`work_id`	Yes
`arguments`	Yes
`read_skills`	Yes	Exact required native skills and their dependencies, copied from the accepted session bootstrap's skills array. Include only entries in that array. General mcp.* guides and native.{studio}.instructions are guidance, not native skill proofs.
`request_key`	Yes
`publication_proposal_id`	No	For native Social scheduling, the exact server-approved publication proposal. This identifier cannot confer approval by itself.
`expected_catalog_version`	Yes	For a new session, read a studios/{studio}/native/{pack} child toolset and copy invocation.catalog_version from a native tool descriptor. Do not use the top-level library version. For calls in an existing session, use that session proposal's catalog_version.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 5, 2026

addedInput schema / properties / arguments / properties / videoPlan

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "prompt": {
+      "minLength": 1,
+      "type": "string"
+    },
+    "referenceSourceIds": {
+      "items": {
+        "maxLength": 200,
+        "minLength": 1,
+        "type": "string"
+      },
+      "maxItems": 30,
+      "type": "array"
+    },
+    "settings": {
+      "additionalProperties": false,
+      "properties": {
+        "aspectRatio": {
+          "default": "9:16",
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "audioProvider": {
+          "default": "fal_seed_audio",
+          "enum": [
+            "fal_seed_audio"
+          ],
+          "type": "string"
+        },
+        "durationSeconds": {
+          "default": 6,
+          "exclusiveMinimum": 0,
+          "maximum": 600,
+          "type": "number"
+        },
+        "imageProvider": {
+          "default": "openai_gpt_image_25_sunburst",
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "quality": {
+          "default": "medium",
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "resolution": {
+          "default": "1K",
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "seedanceLevel": {
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "speed": {
+          "default": 1,
+          "maximum": 2,
+          "minimum": 0.5,
+          "type": "number"
+        },
+        "videoMode": {
+          "enum": [
+            "text_to_video",
+            "image_to_video",
+            "reference_to_video"
+          ],
+          "type": "string"
+        },
+        "videoProvider": {
+          "default": "seedance",
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "videoQuality": {
+          "default": "preview",
+          "enum": [
+            "draft",
+            "preview",
+            "final"
+          ],
+          "type": "string"
+        },
+        "videoResolution": {
+          "default": "720p",
+          "maxLength": 200,
+          "minLength": 1,
+          "type": "string"
+        },
+        "voiceDescription": {
+          "default": "",
+          "type": "string"
+        }
+      },
+      "type": "object"
+    },
+    "title": {
+      "maxLength": 200,
+      "minLength": 1,
+      "type": "string"
+    }
+  },
+  "required": [
+    "title",
+    "prompt"
+  ],
+  "type": "object"
+}

changedInput schema / properties / arguments / required

Previous value: -[
-  "operationId",
-  "brief",
-  "concept",
-  "variant",
-  "media"
-]New value: +[
+  "operationId"
+]

Changed3 schema fields changedNov 5, 2026
- addedInput schema / properties / arguments / properties / media / properties / body / properties / settings / default / seedanceLevel
```
Added value: +"mini_480p"
```
- addedInput schema / properties / arguments / properties / media / properties / body / properties / settings / default / videoQuality
```
Added value: +"draft"
```
- addedInput schema / properties / arguments / properties / media / properties / body / properties / settings / default / videoResolution
```
Added value: +"480p"
```
First observedNov 5, 2026

TDQS

A3.6/5.0

Behavior4/5

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

Annotations already flag this as destructive and idempotent; the description adds genuine context beyond them: everything is saved 'atomically', no generation is started, and the call 'ends this response', which is important terminal behavior an agent would otherwise not know. It stops short of saying what an atomic failure leaves behind or which existing records are overwritten.

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?

Every sentence carries load and the purpose leads. The middle clauses are telegraphic ('For a new video supply operationId and videoPlan {title, prompt}') and the density makes the two operating modes harder to extract than a short enumerated form would be.

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

Completeness3/5

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

An output schema exists, so return values need no explanation, and the description covers both modes plus the default-media behavior. But for a tool that atomically writes four revision-bound records plus a quote and card, the description leaves unclear what the agent should do on a revision conflict and what 'approval card' actually authorizes.

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?

With schema coverage at 50% and heavy nesting, the description does useful work: it explains that videoPlan needs only title and prompt, that settings should be included 'only for explicit creator choices', and that referenceSourceIds are for known reviewed sources only. It says nothing about the harness parameters (work_id, request_key, expected_catalog_version, read_skills) beyond what their schema descriptions already give, and 'revision-bound' is the only hint at how expectedRevision fields behave.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific verb and two concrete artifacts: it prepares 'the exact system quote and approval card' rather than merely saving records, which separates it from the many native.save_genads_* siblings. It also states what it does not do ('Starts no generation'), though the jargon 'exact system quote' and 'approval card' is never defined for an agent that has not seen this family before.

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

Usage Guidelines3/5

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

There is real routing guidance in 'without exploratory reads now' and in the split between the new-video path (operationId + videoPlan) and the existing-creative/still path (full revision-bound setup). However, no sibling is ever named, so an agent cannot tell from the text whether genads_quote_generation, genads_quote_export, or prepare_work is the better call in an ambiguous case.

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

All GenFlick 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.

Resources

Need Help?