StackFast FractWin Expert Brain

Preview CogentCast Package

cogentcast_package_preview

Read-onlyIdempotent

Validate a Work Sample, content_type=narration_review, or content_type=audiobook_production configuration without creating state or vendor cost. A failed preview returns no creation-authorizing digest or authoritative cost estimate. Audiobook Production v1 reuses this five-tool surface: content_type=audiobook_production registers exact manuscript/script/SSML plus provenance, pronunciation, visual/companion, and deterministic-build receipts at zero cost; production.status returns the current derivative and Chief Editor/Gemini/ear/paid/publication gates. Paid canary, full generation, and publication are distinct receipt-gated stages. Uses the existing CogentCast production service; it does not bypass Studio, mint Chief Editor/Robert approval, substitute model output for human authority, publish publicly, or expose credentials.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`input`	Yes	CogentCast Work Sample, private narration review, or zero-cost governed audiobook preparation input. The selected mode is validated by the production service before state or vendor cost is created.

Output Schema

TableJSON Schema

Name	Required	Description	Default
`ok`	Yes
`error`	No
`result`	No
`gateway_receipt`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed5 schema fields changedAug 30, 2026

addedInput schema / additionalProperties
```
Added value: +false
```
addedInput schema / properties / input / additionalProperties
```
Added value: +true
```

addedInput schema / properties / input / description

Added value: +"CogentCast Work Sample, private narration review, or zero-cost governed audiobook preparation input. The selected mode is validated by the production service before state or vendor cost is created."

addedInput schema / properties / input / properties

Added value: +{
+  "article_state": {
+    "enum": [
+      "planned"
+    ],
+    "type": "string"
+  },
+  "article_url": {
+    "format": "uri",
+    "type": "string"
+  },
+  "audience": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "avatar_profile": {
+    "type": "string"
+  },
+  "content_type": {
+    "enum": [
+      "work_sample",
+      "narration_review",
+      "audiobook_production"
+    ],
+    "type": "string"
+  },
+  "cta_url": {
+    "description": "Optional for private author review. When present, HTTPS with a non-root path is required. Metadata only; never spoken.",
+    "format": "uri",
+    "type": "string"
+  },
+  "deck": {
+    "additionalProperties": false,
+    "description": "A real Office Open XML .pptx container. Deck text is visual input and is never spoken.",
+    "properties": {
+      "content_base64": {
+        "description": "RFC 4648 base64 of the raw file bytes; do not base64-encode an existing .b64 text file.",
+        "minLength": 4,
+        "type": "string"
+      },
+      "file_size": {
+        "description": "Decoded byte length. It must equal the raw file size.",
+        "maximum": 10000000,
+        "minimum": 1,
+        "type": "integer"
+      },
+      "filename": {
+        "description": "Original filename, including .md for narration or .pptx for the deck.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "mime_type": {
+        "description": "IANA media type matching the supplied file.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "sha256": {
+        "description": "SHA-256 of the decoded raw file bytes.",
+        "pattern": "^[a-fA-F0-9]{64}$",
+        "type": "string"
+      },
+      "version": {
+        "description": "Caller-controlled immutable source version label.",
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "filename",
+      "mime_type",
+      "content_base64",
+      "file_size",
+      "sha256",
+      "version"
+    ],
+    "type": "object"
+  },
+  "disclosure": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "format": {
+    "enum": [
+      "16:9",
+      "9:16"
+    ],
+    "type": "string"
+  },
+  "historical_derivatives": {
+    "items": {
+      "additionalProperties": true,
+      "type": "object"
+    },
+    "type": "array"
+  },
+  "idempotency_key": {
+    "type": "string"
+  },
+  "intended_visibility": {
+    "enum": [
+      "private",
+      "unlisted"
+    ],
+    "type": "string"
+  },
+  "internal_links": {
+    "items": {
+      "format": "uri",
+      "type": "string"
+    },
+    "type": "array"
+  },
+  "lineage_id": {
+    "type": "string"
+  },
+  "pacing_profile": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "preparation": {
+    "additionalProperties": true,
+    "description": "Exact source/script/SSML and preparation artifact hashes plus 100% provenance, zero unresolved pronunciation, complete visual classification, deterministic regeneration, and governance-test counts.",
+    "type": "object"
+  },
+  "publication_authority": {
+    "const": false,
+    "type": "boolean"
+  },
+  "script": {
+    "additionalProperties": false,
+    "description": "Canonical Markdown narration source. Markdown syntax, front matter, hidden notes, production notes, URLs, and metadata are never spoken.",
+    "properties": {
+      "content_base64": {
+        "description": "RFC 4648 base64 of the raw file bytes; do not base64-encode an existing .b64 text file.",
+        "minLength": 4,
+        "type": "string"
+      },
+      "file_size": {
+        "description": "Decoded byte length. It must equal the raw file size.",
+        "maximum": 10000000,
+        "minimum": 1,
+        "type": "integer"
+      },
+      "filename": {
+        "description": "Original filename, including .md for narration or .pptx for the deck.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "mime_type": {
+        "description": "IANA media type matching the supplied file.",
+        "minLength": 1,
+        "type": "string"
+      },
+      "sha256": {
+        "description": "SHA-256 of the decoded raw file bytes.",
+        "pattern": "^[a-fA-F0-9]{64}$",
+        "type": "string"
+      },
+      "version": {
+        "description": "Caller-controlled immutable source version label.",
+        "minLength": 1,
+        "type": "string"
+      }
+    },
+    "required": [
+      "filename",
+      "mime_type",
+      "content_base64",
+      "file_size",
+      "sha256",
+      "version"
+    ],
+    "type": "object"
+  },
+  "title": {
+    "type": "string"
+  },
+  "topic_image": {
+    "format": "uri",
+    "type": "string"
+  },
+  "voice_profile": {
+    "minLength": 1,
+    "type": "string"
+  }
+}

addedInput schema / properties / input / required
```
Added value: +[
+  "content_type"
+]
```

Changed3 schema fields changedAug 13, 2026

addedOutput schema / oneOf

Added value: +[
+  {
+    "required": [
+      "result"
+    ]
+  },
+  {
+    "required": [
+      "error"
+    ]
+  }
+]

addedOutput schema / properties / error
```
Added value: +{
+  "type": "string"
+}
```

changedOutput schema / required

Previous value: -[
-  "ok",
-  "result",
-  "gateway_receipt"
-]New value: +[
+  "ok",
+  "gateway_receipt"
+]

AddedAug 12, 2026

TDQS

A4.1/5.0

Behavior5/5

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

Annotations already provide readOnlyHint=true, idempotentHint=true, and destructiveHint=false, and the description adds substantial non-obvious behavior: failed previews return no creation-authorizing digest or authoritative cost estimate, audiobook production mode operates at zero cost, and the tool does not mint approvals, publish publicly, or expose credentials. This goes well beyond the structured hints.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness2/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The first sentence is a strong front-loaded purpose statement, but the rest of the paragraph becomes dense and tangential, especially the 'Audiobook Production v1 reuses this five-tool surface' and 'production.status returns...' material. Most of that ecosystem context could be condensed or moved elsewhere; the description is not concise relative to the actual invocation task.

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?

For a single-parameter tool with a rich schema and an output schema, the description together with annotations covers the essential invocation context: mutability, cost, failure response, and approval/publication boundaries. Nothing critical is missing, though the workflow digression slightly obscures the otherwise complete picture.

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 description coverage is 100%, and the schema itself thoroughly documents the nested `input` object and its fields. The description adds mode-specific context for `content_type` values and some failure semantics, but it does not meaningfully clarify the many optional parameters. The schema carries the parameter-semantics burden, so the baseline 3 is appropriate.

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 description opens with a specific verb and resource: 'Validate a Work Sample, content_type=narration_review, or content_type=audiobook_production configuration without creating state or vendor cost.' It clearly identifies the supported modes and contrasts with the mutation-oriented sibling tools by emphasizing that this is a preview/validation action, not a creation or production run.

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?

The first sentence establishes the core usage context: use this tool to validate a configuration before any state or vendor cost is incurred. The negative boundaries — no Studio bypass, no Chief Editor/Robert approval minting, no publication, no credential exposure — tell the agent what this tool cannot be used for. However, it never explicitly names alternatives like cogentcast_package_create or cogentcast_production_run for the actual creation/full-generation steps, so sibling routing is implied rather than fully explicit.

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

All StackFast FractWin Expert Brain 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?