Narrareach

Get draft

get_draft

Read-only

Get a single draft by id, including full HTML content. kind is note for a Note (saved as one, or only ever scheduled as one) and article otherwise. substackControls summarizes the cover, access (audience: freewall, paywall, paid_subscribers or everyone), Subscribe button count, leftover placement text, and what public and paid readers will see; check it before scheduling an article.

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": {
      "id": "<id>"
    },
    "name": "get_draft"
  }
}

Input Schema

Name	Required	Description	Default
`id`	Yes	Draft id.

Output Schema

Name	Required	Description
`id`	Yes
`kind`	Yes
`meta`	Yes	A JSON value stored by Narrareach.
`title`	Yes
`status`	Yes
`createdAt`	Yes
`updatedAt`	Yes
`contentHtml`	Yes
`contentJson`	Yes	A JSON value stored by Narrareach.
`publishedTo`	Yes
`aiVisibility`	Yes
`publishedCount`	Yes
`lastPublishedAt`	Yes
`connectedAccount`	No
`substackControls`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedNov 9, 2026

addedOutput schema / properties / kind

Added value: +{
+  "enum": [
+    "note",
+    "article"
+  ],
+  "type": "string"
+}

changedOutput schema / required

Previous value: -[
-  "id",
-  "title",
-  "status",
-  "createdAt",
-  "updatedAt",
-  "publishedTo",
-  "publishedCount",
-  "lastPublishedAt",
-  "contentHtml",
-  "contentJson",
-  "meta",
-  "aiVisibility",
-  "substackControls"
-]New value: +[
+  "id",
+  "title",
+  "kind",
+  "status",
+  "createdAt",
+  "updatedAt",
+  "publishedTo",
+  "publishedCount",
+  "lastPublishedAt",
+  "contentHtml",
+  "contentJson",
+  "meta",
+  "aiVisibility",
+  "substackControls"
+]

Changed2 schema fields changedOct 30, 2026

addedOutput schema / properties / substackControls

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "audience": {
+      "enum": [
+        "freewall",
+        "paywall",
+        "paid_subscribers",
+        "everyone",
+        "not_applicable"
+      ],
+      "type": "string"
+    },
+    "coverImage": {
+      "anyOf": [
+        {
+          "type": "string"
+        },
+        {
+          "type": "null"
+        }
+      ]
+    },
+    "placementPlaceholders": {
+      "type": "integer"
+    },
+    "readerViews": {
+      "additionalProperties": false,
+      "properties": {
+        "paidSubscribers": {
+          "type": "string"
+        },
+        "publicReaders": {
+          "type": "string"
+        }
+      },
+      "required": [
+        "publicReaders",
+        "paidSubscribers"
+      ],
+      "type": "object"
+    },
+    "subscribeButtons": {
+      "type": "integer"
+    }
+  },
+  "required": [
+    "coverImage",
+    "audience",
+    "subscribeButtons",
+    "placementPlaceholders",
+    "readerViews"
+  ],
+  "type": "object"
+}

changedOutput schema / required

Previous value: -[
-  "id",
-  "title",
-  "status",
-  "createdAt",
-  "updatedAt",
-  "publishedTo",
-  "publishedCount",
-  "lastPublishedAt",
-  "contentHtml",
-  "contentJson",
-  "meta",
-  "aiVisibility"
-]New value: +[
+  "id",
+  "title",
+  "status",
+  "createdAt",
+  "updatedAt",
+  "publishedTo",
+  "publishedCount",
+  "lastPublishedAt",
+  "contentHtml",
+  "contentJson",
+  "meta",
+  "aiVisibility",
+  "substackControls"
+]

Changed2 schema fields changedOct 20, 2026

addedOutput schema / properties / aiVisibility

Added value: +{
+  "anyOf": [
+    {
+      "additionalProperties": false,
+      "properties": {
+        "checks": {
+          "items": {
+            "additionalProperties": false,
+            "properties": {
+              "detail": {
+                "type": "string"
+              },
+              "id": {
+                "type": "string"
+              },
+              "status": {
+                "enum": [
+                  "pass",
+                  "weak",
+                  "missing"
+                ],
+                "type": "string"
+              }
+            },
+            "required": [
+              "id",
+              "status",
+              "detail"
+            ],
+            "type": "object"
+          },
+          "type": "array"
+        },
+        "guidance": {
+          "type": "string"
+        },
+        "needsJudgment": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "topFixes": {
+          "items": {
+            "type": "string"
+          },
+          "type": "array"
+        },
+        "wordCount": {
+          "type": "integer"
+        }
+      },
+      "required": [
+        "wordCount",
+        "checks",
+        "topFixes",
+        "needsJudgment",
+        "guidance"
+      ],
+      "type": "object"
+    },
+    {
+      "type": "null"
+    }
+  ]
+}

changedOutput schema / required

Previous value: -[
-  "id",
-  "title",
-  "status",
-  "createdAt",
-  "updatedAt",
-  "publishedTo",
-  "publishedCount",
-  "lastPublishedAt",
-  "contentHtml",
-  "contentJson",
-  "meta"
-]New value: +[
+  "id",
+  "title",
+  "status",
+  "createdAt",
+  "updatedAt",
+  "publishedTo",
+  "publishedCount",
+  "lastPublishedAt",
+  "contentHtml",
+  "contentJson",
+  "meta",
+  "aiVisibility"
+]

First observedOct 1, 2026

TDQS

A4.1/5.0

Behavior4/5

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

Annotations already declare this a safe read operation (readOnlyHint=true, destructiveHint=false, openWorldHint=false), so the description is free to spend its words on field semantics instead. It does that well, spelling out what kind means and enumerating the audience values freewall, paywall, paid_subscribers, and everyone, which is behavior an annotation cannot convey.

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?

The core action and scope are front-loaded in the first clause, and the trailing clauses are dense with substantive field meaning rather than filler. It is a single long sentence, though, and the audience enumeration could be tightened without losing information.

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?

Return values are covered by an output schema, so the description does not need to restate them, and it instead highlights the field most likely to change agent behavior before a scheduling call. Minor gaps remain: it does not say what happens for an unknown id or whether reader-reply drafts are excluded, which matters given the reply-draft siblings.

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?

There is a single required parameter and schema description coverage is 100%, so the schema already fully documents id. The description's explanation of kind and substackControls concerns return fields rather than the id argument, so it adds nothing beyond the baseline for input semantics.

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: 'Get a single draft by id, including full HTML content.' That is unambiguously different from the sibling writers (update_draft, archive_draft) and from list-style siblings, and it also tells the agent what the returned payload centers on.

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?

It gives one explicit conditional instruction: 'check it before scheduling an article,' tied to the substackControls field. That is real when-to-use guidance, but there are no stated exclusions or named alternatives (for example, when to use list-style tools instead), so it stops short of a 5.

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

All Narrareach 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?