Atwork

Read Workflow

workflow.read

Read-onlyIdempotent

Read a workflow's draft: its sheet, trigger, every step with its ref, name, type, config, onError (if the action fails, on the steps that have it) and next (port → ref, an error branch on port error), and its state. Read it before workflow.update and name steps by these refs.

Input Schema

Name	Required	Description	Default
`workflowId`	Yes

Output Schema

Name	Required	Description
`name`	Yes
`nodes`	Yes	Every step after the trigger, in canvas order
`sheet`	Yes
`state`	Yes
`trigger`	Yes
`workflowId`	Yes
`description`	No

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 8, 2026

addedOutput schema / properties / nodes / items / properties / onError

Added value: +{
+  "description": "If the action fails (integration_action, agent, transcribe and run_workflow steps only): stop, continue (skip failed items) or fallback_path (error branch, its steps on port `error` in next)",
+  "enum": [
+    "stop",
+    "continue",
+    "fallback_path"
+  ],
+  "type": "string"
+}

changedOutput schema / properties / trigger / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "config": {
-        "additionalProperties": {},
-        "description": "Secrets (authorization, API keys, tokens) read as ••••••; send them back unchanged to keep them",
-        "propertyNames": {
-          "type": "string"
-        },
-        "type": "object"
-      },
-      "name": {
-        "type": "string"
-      },
-      "next": {
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "port": {
-              "type": "string"
-            },
-            "ref": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "port",
-            "ref"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "operation": {
-        "type": "string"
-      },
-      "ref": {
-        "description": "The node's id: name it in workflow.update as after, ref or {{steps.<ref>.<path>}}",
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "ref",
-      "name",
-      "type",
-      "config",
-      "next"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "config": {
+        "additionalProperties": {},
+        "description": "Secrets (authorization, API keys, tokens) read as ••••••; send them back unchanged to keep them",
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "name": {
+        "type": "string"
+      },
+      "next": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "port": {
+              "type": "string"
+            },
+            "ref": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "port",
+            "ref"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "onError": {
+        "description": "If the action fails (integration_action, agent, transcribe and run_workflow steps only): stop, continue (skip failed items) or fallback_path (error branch, its steps on port `error` in next)",
+        "enum": [
+          "stop",
+          "continue",
+          "fallback_path"
+        ],
+        "type": "string"
+      },
+      "operation": {
+        "type": "string"
+      },
+      "ref": {
+        "description": "The node's id: name it in workflow.update as after, ref or {{steps.<ref>.<path>}}",
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "ref",
+      "name",
+      "type",
+      "config",
+      "next"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

Changed2 schema fields changedNov 4, 2026

addedOutput schema / properties / nodes / items / properties / config / description

Added value: +"Secrets (authorization, API keys, tokens) read as ••••••; send them back unchanged to keep them"

changedOutput schema / properties / trigger / anyOf

Previous value: -[
-  {
-    "additionalProperties": false,
-    "properties": {
-      "config": {
-        "additionalProperties": {},
-        "propertyNames": {
-          "type": "string"
-        },
-        "type": "object"
-      },
-      "name": {
-        "type": "string"
-      },
-      "next": {
-        "items": {
-          "additionalProperties": false,
-          "properties": {
-            "port": {
-              "type": "string"
-            },
-            "ref": {
-              "type": "string"
-            }
-          },
-          "required": [
-            "port",
-            "ref"
-          ],
-          "type": "object"
-        },
-        "type": "array"
-      },
-      "operation": {
-        "type": "string"
-      },
-      "ref": {
-        "description": "The node's id: name it in workflow.update as after, ref or {{steps.<ref>.<path>}}",
-        "type": "string"
-      },
-      "type": {
-        "type": "string"
-      }
-    },
-    "required": [
-      "ref",
-      "name",
-      "type",
-      "config",
-      "next"
-    ],
-    "type": "object"
-  },
-  {
-    "type": "null"
-  }
-]New value: +[
+  {
+    "additionalProperties": false,
+    "properties": {
+      "config": {
+        "additionalProperties": {},
+        "description": "Secrets (authorization, API keys, tokens) read as ••••••; send them back unchanged to keep them",
+        "propertyNames": {
+          "type": "string"
+        },
+        "type": "object"
+      },
+      "name": {
+        "type": "string"
+      },
+      "next": {
+        "items": {
+          "additionalProperties": false,
+          "properties": {
+            "port": {
+              "type": "string"
+            },
+            "ref": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "port",
+            "ref"
+          ],
+          "type": "object"
+        },
+        "type": "array"
+      },
+      "operation": {
+        "type": "string"
+      },
+      "ref": {
+        "description": "The node's id: name it in workflow.update as after, ref or {{steps.<ref>.<path>}}",
+        "type": "string"
+      },
+      "type": {
+        "type": "string"
+      }
+    },
+    "required": [
+      "ref",
+      "name",
+      "type",
+      "config",
+      "next"
+    ],
+    "type": "object"
+  },
+  {
+    "type": "null"
+  }
+]

AddedOct 27, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), so the bar is lower. The description adds genuinely useful behavior beyond them: this reads the DRAFT rather than the published version, and it discloses the shape of error handling (`onError`, error branch on port `error`), which the agent would otherwise have to discover from the output schema.

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?

One dense, front-loaded sentence: the purpose and returned fields come first, then the usage rule at the end. Every clause carries information, though the parenthetical field enumeration makes it heavy to parse on first read.

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?

An output schema exists, so the return-value enumeration is partly redundant, but it usefully orients the agent before the call. For a single-parameter read tool the definition is nearly complete; the only real gap is the absence of any guidance on sourcing the workflowId or on what happens with an invalid ID.

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 0% and the single parameter workflowId is documented nowhere in the schema, so the description would need to compensate. It never explains what workflowId is or how to obtain one (presumably from workflow.list), leaving that inference to the agent. The parameter name is self-explanatory enough that this is adequate rather than damaging.

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?

States a specific verb and resource ('Read a workflow's draft') with a scope qualifier that separates it from reading a published workflow. The description then enumerates exactly what is returned (sheet, trigger, steps, onError, next, state), so an agent knows precisely what this tool yields versus siblings like workflow.list or workflow.update.

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?

Gives an explicit sequencing rule: 'Read it before workflow.update and name steps by these refs', which tells the agent when this tool must be called and how its output feeds a later call. It stops short of naming alternatives (e.g. workflow.list for enumerating workflows) or stating when not to use it, so it is strong but not complete.

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

All Atwork 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?