Skip to main content
Glama

Meta Council

by com.meta-council
OverviewDiscussionsAdmin

Create Workflow Template

create_workflow_template

Create a new custom workflow template the caller owns, so a multi-step pipeline can be built in conversation instead of by hand in the browser. Saves the same definition the web builder saves. The slug is derived from the name and is returned — use it with run_workflow. Legacy workflows run in dependency order; steps ready together share one bounded parallel layer, while no depends_on keeps authored list order. Explicitly routed workflows use next_step and bounded quality-gate transitions and cannot mix those fields with depends_on. Requires authentication and the workflows:write scope.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
nameYesTemplate name, e.g. 'Competitor Teardown'. The saved slug is derived from this.
tagsNoOptional tags for discovery.
stepsYesThe pipeline steps, in the order they will run.
domainNoOptional grouping domain, e.g. 'research'. Defaults to 'general'.
descriptionNoOptional description of what the workflow does.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / steps / items / properties / tools
      Added value: +{
+  "description": "Optional subset of persona tools. [] disables tools for supplied-evidence drafts; omission inherits.",
+  "items": {
+    "minLength": 1,
+    "type": "string"
+  },
+  "maxItems": 100,
+  "type": "array",
+  "uniqueItems": true
+}
  2. Changed1 schema field changed
    • changedInput schema / properties / steps / items / properties / depends_on / description
      Previous value: -"Optional ids of steps this one builds on. Legacy DAG workflows execute sequentially in topological dependency order; this does not parallelise execution. Do not combine depends_on with routed fields."New value: +"Optional ids of steps this one builds on. A step starts only once every id it names has finished. Steps ready together share one bounded parallel layer in authored order. A definition with no arrows still runs in list order. Do not combine depends_on with routed fields."
  3. Changed1 schema field changed
    • changedOutput schema / (root)
      Previous value: -{
-  "additionalProperties": false,
-  "properties": {
-    "text": {
-      "type": "string"
-    }
-  },
-  "required": [
-    "text"
-  ],
-  "type": "object"
-}New value: +null
  4. Changed8 schema fields changed
    • addedInput schema / properties / steps / items / allOf
      Added value: +[
+  {
+    "not": {
+      "required": [
+        "id",
+        "step_id"
+      ]
+    }
+  }
+]
    • changedInput schema / properties / steps / items / properties / depends_on / description
      Previous value: -"Optional ids of steps this one builds on. Builder metadata only: it is recorded and returned, and it does NOT reorder or parallelise execution. Steps always run in list order."New value: +"Optional ids of steps this one builds on. Legacy DAG workflows execute sequentially in topological dependency order; this does not parallelise execution. Do not combine depends_on with routed fields."
    • addedInput schema / properties / steps / items / properties / human_gate
      Added value: +{
+  "description": "Require approval from the authenticated human review UI. API-key and MCP callers cannot cross this gate.",
+  "type": "boolean"
+}
    • addedInput schema / properties / steps / items / properties / next_step
      Added value: +{
+  "description": "Optional next step id for an explicitly routed workflow. Do not combine routed fields with depends_on.",
+  "maxLength": 100,
+  "minLength": 1,
+  "pattern": "^(?:__end__|[A-Za-z0-9][A-Za-z0-9_.:-]*)$",
+  "type": "string"
+}
    • addedInput schema / properties / steps / items / properties / quality_gate
      Added value: +{
+  "additionalProperties": false,
+  "allOf": [
+    {
+      "if": {
+        "properties": {
+          "schema": {
+            "const": "scope_decision/v1"
+          }
+        },
+        "required": [
+          "schema"
+        ]
+      },
+      "then": {
+        "properties": {
+          "blocking_severities": {
+            "const": [
+              "P0",
+              "P1"
+            ]
+          },
+          "max_iterations": {
+            "const": 1
+          }
+        }
+      }
+    }
+  ],
+  "properties": {
+    "blocking_severities": {
+      "items": {
+        "enum": [
+          "P0",
+          "P1",
+          "P2",
+          "P3",
+          "P4",
+          "P5"
+        ],
+        "type": "string"
+      },
+      "maxItems": 6,
+      "minItems": 1,
+      "type": "array",
+      "uniqueItems": true
+    },
+    "loop_to": {
+      "maxLength": 100,
+      "minLength": 1,
+      "pattern": "^[A-Za-z0-9][A-Za-z0-9_.:-]*$",
+      "type": "string"
+    },
+    "max_iterations": {
+      "maximum": 5,
+      "minimum": 1,
+      "type": "integer"
+    },
+    "pass_to": {
+      "maxLength": 100,
+      "minLength": 1,
+      "pattern": "^(?:__end__|[A-Za-z0-9][A-Za-z0-9_.:-]*)$",
+      "type": "string"
+    },
+    "schema": {
+      "enum": [
+        "severity_findings/v1",
+        "scope_decision/v1"
+      ],
+      "type": "string"
+    }
+  },
+  "required": [
+    "schema",
+    "loop_to",
+    "pass_to",
+    "max_iterations"
+  ],
+  "type": "object"
+}
    • addedInput schema / properties / steps / items / properties / requires_distinct_provider_from
      Added value: +{
+  "description": "Require this step's actual provider to differ from the provider that produced the named earlier step.",
+  "maxLength": 100,
+  "minLength": 1,
+  "pattern": "^[A-Za-z0-9][A-Za-z0-9_.:-]*$",
+  "type": "string"
+}
    • addedInput schema / properties / steps / items / properties / step_id
      Added value: +{
+  "description": "Canonical stable identifier for routed steps. Do not supply both step_id and the legacy id field.",
+  "maxLength": 100,
+  "minLength": 1,
+  "pattern": "^[A-Za-z0-9][A-Za-z0-9_.:-]*$",
+  "type": "string"
+}
    • changedInput schema / properties / steps / items / properties / type / description
      Previous value: -"Optional kind of node. Defaults to 'agent' -- ask a model a question -- which is the only kind this build can execute. 'transform' and 'connector' are accepted and saved so a workflow authored for a later build round-trips, but a run that reaches one fails that single step with a plain message. Do NOT use them for work that must actually run."New value: +"Optional executable node kind. Defaults to 'agent', which asks a model a question. 'transform' runs a supported deterministic local operation; 'connector' invokes the configured connector runtime and fails that step if the runtime is unavailable."
  5. Changed2 schema fields changed
    • addedInput schema / properties / steps / items / properties / params
      Added value: +{
+  "description": "Optional configuration for a non-agent step. Must be omitted or empty for an 'agent' step, whose configuration is the named fields above (model, temperature, instruction, ...); params would be silently ignored there, so it is refused.",
+  "type": "object"
+}
    • addedInput schema / properties / steps / items / properties / type
      Added value: +{
+  "description": "Optional kind of node. Defaults to 'agent' -- ask a model a question -- which is the only kind this build can execute. 'transform' and 'connector' are accepted and saved so a workflow authored for a later build round-trips, but a run that reaches one fails that single step with a plain message. Do NOT use them for work that must actually run.",
+  "enum": [
+    "agent",
+    "transform",
+    "connector"
+  ],
+  "type": "string"
+}
  6. Added

TDQS

A4.4/5.0
Behavior5/5

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

Adds substantial context beyond the annotations: the required authentication and workflows:write scope, that the saved definition matches the web builder's, that the slug is derived from the name and returned, and the execution semantics (dependency order, bounded parallel layers, list order, and the routed next_step/quality_gate path that cannot mix with depends_on).

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?

Purpose and the slug/run_workflow handoff are front-loaded, and each sentence conveys usable information. It is dense and runs long, but no sentence is filler given the tool's complexity.

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?

With no output schema, the description supplies the missing return information (the derived slug) and covers auth requirements, execution model, and the routing rules an agent needs to author a valid definition. Complete for this tool's complexity.

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 nested step schema is extremely detailed, so the schema carries the parameter burden. The description reiterates the depends_on vs routed-fields exclusivity and the slug derivation, but adds little syntax or format detail beyond what the schema already states.

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?

Opens with a specific verb+resource ('Create a new custom workflow template the caller owns') and adds the scope of what it produces. It clearly distinguishes itself from siblings such as update_workflow_template, plan_workflow, and run_workflow by naming the creation act and the slug handoff.

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 frames the use case ('built in conversation instead of by hand in the browser') and routes the agent forward to run_workflow with the returned slug. It does not, however, contrast against peers like plan_workflow or explain when to use this versus updating an existing template.

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

All Meta Council toolsInspect
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