Postlyra.app — Telegram posts from AI chats

Create a Postlyra post draft

create_post_draft

Use this when creating a Telegram draft. Read get_formatting_capabilities; prefer finished richDocument. Bind mediaFile1..6/mediaFiles via media.src slots. Returns ID, JPEG, preview link and its own card on MCP Apps hosts; do not call show_post_card automatically afterward because it duplicates that card. Keep the link and follow display instructions. Image references/file inputs are validated and imported; direct RichDocument media.src can remain external. Check validation. Never publishes.

Input Schema

TableJSON Schema

Name	Required	Description
`text`	No	Optional user-approved draft text supplied by ChatGPT.
`style`	No	Natural style request from the user, for example beautiful, premium, business, blog, presentation, informal, real-estate, launch, or landing-page-like. Use this as guidance, not literal post copy.
`topic`	Yes
`language`	No
`channelId`	No	Optional owner-bound Postlyra channel id or exact title returned by list_channels.
`structure`	No	Desired content structure in natural language. Mention available facts such as gallery, CTA, comparison, details, map, report, changelog, or before/after.
`mediaFile1`	No	Actual attached or generated image file, up to 10 MiB: JPEG, PNG, GIF or WebP. Pass the file through the client upload mechanism; the server receives download_url and file_id. mime_type and file_name may be omitted. In the same richDocument call, use this slot name as media.src for exact placement.
`mediaFile2`	No	Actual attached or generated image file, up to 10 MiB: JPEG, PNG, GIF or WebP. Pass the file through the client upload mechanism; the server receives download_url and file_id. mime_type and file_name may be omitted. In the same richDocument call, use this slot name as media.src for exact placement.
`mediaFile3`	No	Actual attached or generated image file, up to 10 MiB: JPEG, PNG, GIF or WebP. Pass the file through the client upload mechanism; the server receives download_url and file_id. mime_type and file_name may be omitted. In the same richDocument call, use this slot name as media.src for exact placement.
`mediaFile4`	No	Actual attached or generated image file, up to 10 MiB: JPEG, PNG, GIF or WebP. Pass the file through the client upload mechanism; the server receives download_url and file_id. mime_type and file_name may be omitted. In the same richDocument call, use this slot name as media.src for exact placement.
`mediaFile5`	No	Actual attached or generated image file, up to 10 MiB: JPEG, PNG, GIF or WebP. Pass the file through the client upload mechanism; the server receives download_url and file_id. mime_type and file_name may be omitted. In the same richDocument call, use this slot name as media.src for exact placement.
`mediaFile6`	No	Actual attached or generated image file, up to 10 MiB: JPEG, PNG, GIF or WebP. Pass the file through the client upload mechanism; the server receives download_url and file_id. mime_type and file_name may be omitted. In the same richDocument call, use this slot name as media.src for exact placement.
`mediaFiles`	No	Alternative file array for clients supporting file arrays. Prefer mediaFile1..mediaFile6 otherwise. At most 6 files total across slots and array; use mediaFiles[0] etc. as richDocument src bindings.
`references`	No
`templateId`	No
`formatPreset`	No	Optional Postlyra formatting preset/layout recipe. Leave unset when the user did not name one; Postlyra will infer a recipe from topic, style, structure, and references.
`richDocument`	No	Preferred finished layout: {version:1, blocks:[...]}. Overrides text, template and preset. Call get_formatting_capabilities for exact block/inline schemas and examples. For uploaded images use media.src="mediaFile1" etc. with the corresponding file in this call.
`signatureSelection`	No

Output Schema

TableJSON Schema

Name	Required	Description
`id`	No
`card`	No	Interactive card attachment and fallback instructions. attachedToThisResult means this response already supplies the card; do not automatically call show_post_card again. Host support determines actual rendering.
`text`	No
`title`	No
`locale`	No
`postId`	No
`status`	No
`display`	No
`draftId`	Yes
`message`	Yes
`revision`	No
`richHtml`	No
`channelId`	No
`updatedAt`	No
`previewUrl`	Yes
`screenshot`	No
`mediaStatus`	No	Present only when image inputs were validated and imported into durable storage during this call. It does not describe arbitrary external document media.
`documentJson`	No
`inlineButtons`	No
`screenshotUrl`	No	JPEG screenshot of the saved Telegram preview; null if rendering is temporarily unavailable.
`signatureSnapshot`	No
`signatureSelection`	No
`deliveryDocumentJson`	No	Composed publication including the selected auto-signature. Edit documentJson, never copy this composition into the post body.
`deliveryInlineButtons`	No
`formattingSuggestions`	No	Optional formatting ideas. They do not affect validation, publication or user consent. The user's choice always takes priority.

Schema Changelog

Changes observed during successful MCP inspections.

Changed1 schema field changedOct 14, 2026

changedOutput schema / properties / card / description

Previous value: -"Interactive card availability and fallback instructions. Host UI support determines whether a card can render; preview links remain available."New value: +"Interactive card attachment and fallback instructions. attachedToThisResult means this response already supplies the card; do not automatically call show_post_card again. Host support determines actual rendering."

Changed1 schema field changedOct 14, 2026

addedOutput schema / properties / formattingSuggestions

Added value: +{
+  "additionalProperties": false,
+  "description": "Optional formatting ideas. They do not affect validation, publication or user consent. The user's choice always takes priority.",
+  "properties": {
+    "advisory": {
+      "const": true,
+      "type": "boolean"
+    },
+    "decisionOwner": {
+      "const": "user",
+      "type": "string"
+    },
+    "instruction": {
+      "type": "string"
+    },
+    "items": {
+      "items": {
+        "additionalProperties": false,
+        "properties": {
+          "blockPaths": {
+            "items": {
+              "type": "string"
+            },
+            "maxItems": 5,
+            "type": "array"
+          },
+          "code": {
+            "type": "string"
+          },
+          "message": {
+            "type": "string"
+          },
+          "recommendation": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "code",
+          "message",
+          "recommendation",
+          "blockPaths"
+        ],
+        "type": "object"
+      },
+      "maxItems": 4,
+      "type": "array"
+    }
+  },
+  "required": [
+    "advisory",
+    "decisionOwner",
+    "instruction",
+    "items"
+  ],
+  "type": "object"
+}

Changed6 schema fields changedOct 13, 2026

addedInput schema / properties / references / items / properties / mimeType

Added value: +{
+  "description": "Optional MIME metadata, for example image/png. Identifies extensionless image URLs; actual downloaded bytes are validated.",
+  "maxLength": 128,
+  "type": "string"
+}

changedInput schema / properties / references / items / properties / url / description

Previous value: -"Source URL or direct image URL. Image URLs may be used as media/collage/slideshow inputs when the inferred recipe supports visuals."New value: +"Source page or direct image URL. Image references are downloaded, validated and durably imported. For extensionless image URLs supply mimeType. Other source-page references remain citations."

addedOutput schema / properties / card

Added value: +{
+  "description": "Interactive card availability and fallback instructions. Host UI support determines whether a card can render; preview links remain available.",
+  "type": "object"
+}

addedOutput schema / properties / mediaStatus

Added value: +{
+  "description": "Present only when image inputs were validated and imported into durable storage during this call. It does not describe arbitrary external document media.",
+  "enum": [
+    "imported"
+  ],
+  "type": "string"
+}

addedOutput schema / properties / postId

Added value: +{
+  "maxLength": 128,
+  "minLength": 1,
+  "type": "string"
+}

addedOutput schema / properties / revision

Added value: +{
+  "minimum": 1,
+  "type": "integer"
+}

Changed8 schema fields changedOct 9, 2026

addedInput schema / properties / signatureSelection

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "mode": {
+      "enum": [
+        "inherit",
+        "none",
+        "custom"
+      ],
+      "type": "string"
+    },
+    "signatureId": {
+      "maxLength": 128,
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "mode"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / channelId

Added value: +{
+  "maxLength": 128,
+  "type": [
+    "string",
+    "null"
+  ]
+}

addedOutput schema / properties / deliveryDocumentJson

Added value: +{
+  "description": "Composed publication including the selected auto-signature. Edit documentJson, never copy this composition into the post body.",
+  "type": "object"
+}

addedOutput schema / properties / deliveryInlineButtons

Added value: +{
+  "items": {
+    "anyOf": [
+      {
+        "type": "object"
+      },
+      {
+        "items": {
+          "type": "object"
+        },
+        "type": "array"
+      }
+    ]
+  },
+  "type": "array"
+}

addedOutput schema / properties / inlineButtons / items / anyOf

Added value: +[
+  {
+    "type": "object"
+  },
+  {
+    "items": {
+      "type": "object"
+    },
+    "type": "array"
+  }
+]

removedOutput schema / properties / inlineButtons / items / type
```
Removed value: -"object"
```

addedOutput schema / properties / signatureSelection

Added value: +{
+  "additionalProperties": false,
+  "properties": {
+    "mode": {
+      "enum": [
+        "inherit",
+        "none",
+        "custom"
+      ],
+      "type": "string"
+    },
+    "signatureId": {
+      "maxLength": 128,
+      "type": [
+        "string",
+        "null"
+      ]
+    }
+  },
+  "required": [
+    "mode"
+  ],
+  "type": "object"
+}

addedOutput schema / properties / signatureSnapshot

Added value: +{
+  "type": [
+    "object",
+    "null"
+  ]
+}

First observedSep 11, 2026

TDQS

A4.4/5.0

Behavior5/5

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

Beyond the annotations (readOnly=false, destructive=false, openWorld=true) the description discloses that the call returns an ID, JPEG, preview link and its own card on MCP Apps hosts, that image inputs are validated and durably imported while external media.src may stay external, that validation must be checked, and that it never publishes. These are concrete behavioral facts annotations cannot express.

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 use case is front-loaded and every clause carries operational weight for an 18-parameter tool, so little is wasted. The delivery is a run-on of semicolon-joined imperatives rather than grouped guidance, which costs it a point on structure.

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, nested, openWorld tool with an output schema, the description covers the critical inter-tool dependencies (get_formatting_capabilities, show_post_card suppression, media binding). Minor omissions remain, such as defaulting behavior for style/language and how this tool relates to attach_media_to_draft or preview_post, but nothing needed to call it correctly is missing.

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 72%, and the description adds real meaning on top of it: mediaFile1..6/mediaFiles are bindable as richDocument media.src slots, richDocument overrides text/template/preset, and reference images are downloaded and imported. It does not clarify style vs formatPreset interplay or signatureSelection, but it usefully compensates for the uncovered gaps.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The first clause 'Use this when creating a Telegram draft' names the verb and resource clearly, and 'Never publishes' implicitly distinguishes it from publish_post/schedule_post. However, it never states plainly that the tool *creates* a draft record, so an agent must infer the action from the use-case framing rather than a direct statement.

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?

Explicit routing: use for Telegram drafts, read get_formatting_capabilities first, prefer a finished richDocument, bind media via media.src slots, and specifically do NOT auto-call show_post_card because it duplicates the returned card. This is exactly the when/when-not/alternatives guidance the dimension rewards.

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

All Postlyra.app — Telegram posts from AI chats 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.