Postlyra.app — Telegram posts from AI chats

Edit Postlyra working content

update_post

Destructive

Use when changing a post's working content, title, buttons or attention flag. Read its revision first. Scheduled and sent messages remain on their own snapshots until apply_post_to_publication is requested.

Input Schema

TableJSON Schema

Name	Required	Description
`title`	No
`locale`	No
`postId`	Yes
`documentJson`	No	Full RichDocument from get_formatting_capabilities.
`inlineButtons`	No	Separate Telegram keyboard, normally rows: [[{"text":"Open","url":"https://example.com"}]]. A legacy flat array is also supported. RichDocument button blocks use a different type/value shape.
`needsAttention`	No
`expectedRevision`	Yes

Output Schema

TableJSON Schema

Name	Required	Description	Default
`data`	Yes
`message`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedOct 13, 2026

addedInput schema / properties / inlineButtons / description

Added value: +"Separate Telegram keyboard, normally rows: [[{\"text\":\"Open\",\"url\":\"https://example.com\"}]]. A legacy flat array is also supported. RichDocument button blocks use a different type/value shape."

addedInput schema / properties / inlineButtons / items / anyOf

Added value: +[
+  {
+    "items": {
+      "additionalProperties": true,
+      "properties": {
+        "callbackData": {
+          "type": "string"
+        },
+        "copyText": {
+          "properties": {
+            "text": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "text"
+          ],
+          "type": "object"
+        },
+        "iconCustomEmojiId": {
+          "type": "string"
+        },
+        "loginUrl": {
+          "properties": {
+            "botUsername": {
+              "type": "string"
+            },
+            "forwardText": {
+              "type": "string"
+            },
+            "requestWriteAccess": {
+              "type": "boolean"
+            },
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "url"
+          ],
+          "type": "object"
+        },
+        "style": {
+          "enum": [
+            "primary",
+            "success",
+            "danger"
+          ],
+          "type": "string"
+        },
+        "switchInlineQuery": {
+          "type": "string"
+        },
+        "switchInlineQueryChosenChat": {
+          "properties": {
+            "allowBotChats": {
+              "type": "boolean"
+            },
+            "allowChannelChats": {
+              "type": "boolean"
+            },
+            "allowGroupChats": {
+              "type": "boolean"
+            },
+            "allowUserChats": {
+              "type": "boolean"
+            },
+            "query": {
+              "type": "string"
+            }
+          },
+          "type": "object"
+        },
+        "switchInlineQueryCurrentChat": {
+          "type": "string"
+        },
+        "text": {
+          "description": "Visible button label.",
+          "type": "string"
+        },
+        "type": {
+          "enum": [
+            "url",
+            "web_app",
+            "login_url",
+            "callback_data",
+            "switch_inline_query",
+            "switch_inline_query_current_chat",
+            "switch_inline_query_chosen_chat",
+            "copy_text"
+          ],
+          "type": "string"
+        },
+        "url": {
+          "description": "URL action, e.g. https://example.com. Canonical external keyboard field is url, not RichDocument value.",
+          "type": "string"
+        },
+        "value": {
+          "description": "Compatibility alias for url only when type=url. Prefer url.",
+          "type": "string"
+        },
+        "webApp": {
+          "properties": {
+            "url": {
+              "type": "string"
+            }
+          },
+          "required": [
+            "url"
+          ],
+          "type": "object"
+        }
+      },
+      "required": [
+        "text"
+      ],
+      "type": "object"
+    },
+    "type": "array"
+  },
+  {
+    "additionalProperties": true,
+    "properties": {
+      "callbackData": {
+        "type": "string"
+      },
+      "copyText": {
+        "properties": {
+          "text": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "text"
+        ],
+        "type": "object"
+      },
+      "iconCustomEmojiId": {
+        "type": "string"
+      },
+      "loginUrl": {
+        "properties": {
+          "botUsername": {
+            "type": "string"
+          },
+          "forwardText": {
+            "type": "string"
+          },
+          "requestWriteAccess": {
+            "type": "boolean"
+          },
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "url"
+        ],
+        "type": "object"
+      },
+      "style": {
+        "enum": [
+          "primary",
+          "success",
+          "danger"
+        ],
+        "type": "string"
+      },
+      "switchInlineQuery": {
+        "type": "string"
+      },
+      "switchInlineQueryChosenChat": {
+        "properties": {
+          "allowBotChats": {
+            "type": "boolean"
+          },
+          "allowChannelChats": {
+            "type": "boolean"
+          },
+          "allowGroupChats": {
+            "type": "boolean"
+          },
+          "allowUserChats": {
+            "type": "boolean"
+          },
+          "query": {
+            "type": "string"
+          }
+        },
+        "type": "object"
+      },
+      "switchInlineQueryCurrentChat": {
+        "type": "string"
+      },
+      "text": {
+        "description": "Visible button label.",
+        "type": "string"
+      },
+      "type": {
+        "enum": [
+          "url",
+          "web_app",
+          "login_url",
+          "callback_data",
+          "switch_inline_query",
+          "switch_inline_query_current_chat",
+          "switch_inline_query_chosen_chat",
+          "copy_text"
+        ],
+        "type": "string"
+      },
+      "url": {
+        "description": "URL action, e.g. https://example.com. Canonical external keyboard field is url, not RichDocument value.",
+        "type": "string"
+      },
+      "value": {
+        "description": "Compatibility alias for url only when type=url. Prefer url.",
+        "type": "string"
+      },
+      "webApp": {
+        "properties": {
+          "url": {
+            "type": "string"
+          }
+        },
+        "required": [
+          "url"
+        ],
+        "type": "object"
+      }
+    },
+    "required": [
+      "text"
+    ],
+    "type": "object"
+  }
+]

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

First observedSep 11, 2026

TDQS

A3.9/5.0

Behavior4/5

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

Annotations already declare destructiveHint=true and idempotentHint=false, so the mutation/safety profile is covered. The description adds two useful behavioral facts beyond that: the revision-read prerequisite and the snapshot isolation rule (scheduled/sent messages are untouched until apply_post_to_publication). What a change destroys or how revision conflicts resolve is still unstated.

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?

Three tight sentences, front-loaded with the use-when trigger, followed by the prerequisite and the routing detail. No filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists so return values need not be explained, and annotations carry the safety profile. However, for a tool with complex nested button/document parameters and low schema description coverage, the description is thin on how the working-content payload is structured or replaced.

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 only 29%, so the description should compensate. It names the target fields (title, buttons, attention) but leaves documentJson's full-replace semantics, locale, postId format, and expectedRevision conflict behavior undocumented; "read its revision first" only hints at expectedRevision. The nested schema descriptions for inlineButtons carry most of the load.

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?

States a specific verb (changing) and resource (a post's working content) and enumerates the mutable fields: content, title, buttons, attention flag. It routes the agent toward apply_post_to_publication for propagation, but never distinguishes itself from the close sibling update_post_draft, leaving some ambiguity about which edit tool applies.

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?

"Use when changing..." supplies a clear trigger, "Read its revision first" gives a prerequisite, and the closing sentence names the alternative (apply_post_to_publication) for publishing to scheduled/sent messages. It lacks explicit when-not-to-use guidance or a pointer to update_post_draft.

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.