Skip to main content
Glama
Sign In

Mark

by com.use-mark.app
OverviewDiscussionsAdmin

Edit Published Post

edit_published_post

Replaces the text of a published social post on its platform, right away. The new text goes live as soon as the call returns; it does not go back through review, and it is recorded as a new rev approved by you. Only people who can approve the channel's posts may use it: on a channel set to admins only (approverRole: approver), workspace admins. Text only: media, the first comment, YouTube and Pinterest titles, and X thread replies stay as posted. Works on LinkedIn, Facebook, X, YouTube (the description) and Pinterest (the description, if Pinterest lets apps edit pins). X: single posts only, within 1 hour of going live, up to 5 edits, and the account needs X Premium; X gives the edited post a new address, returned as url. Instagram and TikTok are refused: edit those in their apps. The text gets the same checks as save_post (the channel's character limit and blocked phrases); blank text is refused. Links go out as written, so keep the tracking links from the live text. Drafts, posts not yet published, website pages and external posts are refused, and so is a second edit of the same post while one is in progress. A refusal changes nothing in Mark or on the platform, and the error names the platform and its reason. Two errors are different: if the error says Mark couldn't confirm the platform took the edit, check the live post before calling again; if it says the live post changed but Mark didn't record it, call again with the same text. Related: get_post, save_post, delete_post.

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": {
      "postId": "<postId>",
      "body": "<body>"
    },
    "name": "edit_published_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
bodyYesThe post's full new text. Replaces the live text.
postIdYesThe published social post to edit.

Output Schema

NameRequiredDescriptionDefault
revYesThe new rev, recorded as approved by you.
urlYesThe live post after the edit; new for X.
postIdYes
channelYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedOutput schema / properties / channel / enum
      Previous value: -[
-  "instagram",
-  "facebook",
-  "youtube",
-  "pinterest",
-  "tiktok",
-  "x",
-  "linkedin",
-  "linkedin_article",
-  "blog",
-  "faq",
-  "competitor_page",
-  "landing_page",
-  "email",
-  "meta_ads",
-  "google_ads"
-]New value: +[
+  "instagram",
+  "facebook",
+  "youtube",
+  "pinterest",
+  "tiktok",
+  "x",
+  "linkedin",
+  "linkedin_article",
+  "blog",
+  "faq",
+  "competitor_page",
+  "meta_ads",
+  "google_ads"
+]
  2. Added

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond annotations: the edit goes live immediately, skips review, is recorded as a new approved revision, and requires channel-approver permission. It discloses the non-idempotency ('second edit of the same post while one is in progress' refused), error semantics (nothing changes on refusal; the two distinct ambiguous-outcome errors and how to recover), and precise field-preservation rules. This aligns with and enriches the destructiveHint=false / idempotentHint=false / openWorldHint=true annotations without contradicting them.

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?

Front-loads the core action and timing, then layers constraints. Dense and mostly earning its place, though it is long and the recovery guidance for the two error cases could be tighter; still, the length is justified by the platform-specific edge cases.

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?

Given a mutation tool with an output schema already handling return values, the description covers permissions, platform allow/deny lists, per-platform constraints, validation, field preservation, and error recovery. An agent has everything needed to call it correctly or decline.

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 100%, so baseline is 3, and the description adds real meaning: body gets the same checks as save_post (character limit, blocked phrases), blank text refused, and links go out as written (keep tracking links). It enriches interpretation of body beyond the schema's 'full new text' without over-explaining.

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 ('replaces the text') and resource ('a published social post on its platform') with immediate timing. It is clearly distinguishable from save_post, approve_posts, submit_post, or delete_post by operating on an already-live post in place. Scope (text only) is stated up front.

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 when-to-use and when-not: drafts, unpublished posts, website pages, and external posts are refused; Instagram and TikTok are refused with a pointed alternative ('edit those in their apps'). It also enumerates platform conditions (X single posts, 1-hour window, 5-edit cap, Premium) and names related tools (get_post, save_post, delete_post), leaving little to inference.

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

All Mark 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