Treza

Create pipeline

create_pipeline

Create a new pipeline (as a draft) on your Treza account, from a template (templateId, see list_pipeline_templates) or with an initial node graph. Use list_node_types / get_node_type to learn the graph vocabulary: every edge names the two nodes it joins and a port on each, e.g. {"source":"music","sourceHandle":"audio","target":"sequence","targetHandle":"shots"}. A graph with error-level issues is refused with every issue listed, and nothing is saved. That includes a config key the node does not define, a value outside a field's options or range, and a model id, duration, aspect ratio or voice the chosen model does not offer: pick them from get_node_type. Drafts can be run with run_pipeline; publish_pipeline makes them invokable over the public API. To put music under a video the account already has, call assemble_video with musicPrompt instead of building a graph.

Input Schema

TableJSON Schema

Name	Required	Description
`name`	Yes
`edges`	No	Wires between node ports, e.g. {"source":"music","sourceHandle":"audio","target":"sequence","targetHandle":"shots"}. Pass together with nodes; [] for none.
`nodes`	No	The graph's nodes. Pass together with edges.
`templateId`	No	Copy this template's graph (ids from list_pipeline_templates). Ignored when nodes/edges are supplied.
`description`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedSep 25, 2026

changedInput schema / properties / edges / items / properties / sourceHandle / description

Previous value: -"Output port on the source node: an `outputs` id from get_node_type, e.g. \"audio\" on music-gen or \"video\" on sequence. \"out\" is the generic output the canvas draws."New value: +"Output port on the source node: an `outputs` id from get_node_type, e.g. \"audio\" on music-gen or \"video\" on sequence. \"out\" is the generic output the canvas draws; name the port instead on a node with more than one output besides \"result\" (update_pipeline refuses a new generic wire there)."

changedInput schema / properties / edges / items / properties / targetHandle / description

Previous value: -"Input port on the target node: an `inputs` id from get_node_type, e.g. \"shots\" on sequence or \"prompt\" on music-gen. \"in\" is the generic input the canvas draws, which picks a port by media type at run time; name the port whenever the target has more than one input."New value: +"Input port on the target node: an `inputs` id from get_node_type, e.g. \"shots\" on sequence or \"prompt\" on music-gen. \"in\" is the generic input the canvas draws, which guesses a port by media type at run time; name the port instead on a node with more than one input (update_pipeline refuses a new generic wire there)."

Changed11 schema fields changedSep 24, 2026

addedInput schema / properties / edges / description

Added value: +"Wires between node ports, e.g. {\"source\":\"music\",\"sourceHandle\":\"audio\",\"target\":\"sequence\",\"targetHandle\":\"shots\"}. Pass together with nodes; [] for none."

changedInput schema / properties / edges / items / additionalProperties
```
Previous value: -{}New value: +false
```

addedInput schema / properties / edges / items / description

Added value: +"A wire from one node's output port to another node's input port. An edge is {\"source\": node id, \"sourceHandle\": output port id, \"target\": node id, \"targetHandle\": input port id, \"id\": optional unique id}, e.g. {\"source\":\"music\",\"sourceHandle\":\"audio\",\"target\":\"sequence\",\"targetHandle\":\"shots\"}. Port ids are the ones get_node_type lists under outputs and inputs."

addedInput schema / properties / edges / items / properties

Added value: +{
+  "id": {
+    "description": "Unique id for this wire. Assigned when omitted.",
+    "minLength": 1,
+    "type": "string"
+  },
+  "source": {
+    "description": "Id of the node the wire leaves, as given in `nodes`.",
+    "minLength": 1,
+    "type": "string"
+  },
+  "sourceHandle": {
+    "description": "Output port on the source node: an `outputs` id from get_node_type, e.g. \"audio\" on music-gen or \"video\" on sequence. \"out\" is the generic output the canvas draws.",
+    "minLength": 1,
+    "type": "string"
+  },
+  "target": {
+    "description": "Id of the node the wire enters, as given in `nodes`.",
+    "minLength": 1,
+    "type": "string"
+  },
+  "targetHandle": {
+    "description": "Input port on the target node: an `inputs` id from get_node_type, e.g. \"shots\" on sequence or \"prompt\" on music-gen. \"in\" is the generic input the canvas draws, which picks a port by media type at run time; name the port whenever the target has more than one input.",
+    "minLength": 1,
+    "type": "string"
+  }
+}

removedInput schema / properties / edges / items / propertyNames
```
Removed value: -{
-  "type": "string"
-}
```

addedInput schema / properties / edges / items / required

Added value: +[
+  "source",
+  "sourceHandle",
+  "target",
+  "targetHandle"
+]

addedInput schema / properties / nodes / description

Added value: +"The graph's nodes. Pass together with edges."

addedInput schema / properties / nodes / items / description

Added value: +"One node: an id, a type from list_node_types, and its config."

addedInput schema / properties / nodes / items / properties

Added value: +{
+  "config": {
+    "additionalProperties": {},
+    "description": "Settings, as get_node_type's configSchema describes them. A node this call adds starts from its type's defaults, and what you pass overrides them.",
+    "propertyNames": {
+      "type": "string"
+    },
+    "type": "object"
+  },
+  "id": {
+    "description": "Unique id. Edges, and run_pipeline inputs, refer to the node by it.",
+    "minLength": 1,
+    "type": "string"
+  },
+  "label": {
+    "description": "Name shown on the canvas.",
+    "type": "string"
+  },
+  "position": {
+    "description": "Canvas position. Laid out automatically when omitted.",
+    "properties": {
+      "x": {
+        "type": "number"
+      },
+      "y": {
+        "type": "number"
+      }
+    },
+    "required": [
+      "x",
+      "y"
+    ],
+    "type": "object"
+  },
+  "type": {
+    "description": "A node type from list_node_types, e.g. \"file\", \"music-gen\", \"sequence\", \"output\".",
+    "minLength": 1,
+    "type": "string"
+  }
+}

removedInput schema / properties / nodes / items / propertyNames
```
Removed value: -{
-  "type": "string"
-}
```
addedInput schema / properties / nodes / items / required
```
Added value: +[
+  "id",
+  "type"
+]
```

First observedSep 21, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Annotations are all false and offer no safety profile, so the description carries the full behavioral burden. It discloses that creation is a draft, that error-level issues cause refusal with every issue listed and 'nothing is saved,' and details the validation rules (config keys, value ranges, model-specific options). It also clarifies lifecycle: drafts can be run and published, which is beyond what annotations provide.

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

Conciseness5/5

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

The description is well-structured: main purpose first, then vocabulary, validation behavior, lifecycle, and alternative tool. Every sentence earns its place, and the embedded edge example is compact and illustrative. No redundancy or 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?

For a complex graph-creation tool with no output schema and no annotation support, the description covers creation modes, validation, and downstream steps thoroughly. The main gap is the lack of an explicit statement about the return value (e.g., the created pipeline object or id), which an agent would need to know to use the result effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 60%, so the description must add meaning. It explains the templateId-versus-nodes/edges decision, gives an explicit edge example, and directs users to get_node_type for valid config values and port names. This goes beyond the schema's structural descriptions, though it does not fully document every parameter edge case.

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 states a specific verb and resource ('Create a new pipeline (as a draft) on your Treza account') and distinguishes from siblings by naming run_pipeline, publish_pipeline, and assemble_video with clear contrast. It also references list_pipeline_templates and list_node_types, making the tool's role unambiguous.

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?

Gives explicit when-to-use guidance: create from a template (templateId) or with a node graph, and points to list_node_types/get_node_type for vocabulary. It also states when not to use it ('To put music under a video the account already has, call assemble_video with musicPrompt instead of building a graph') and outlines follow-up steps (run_pipeline, publish_pipeline).

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

All Treza 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.

Create pipeline

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources