Skip to main content
Glama
Upload-Post

Upload-Post

Official

Edit a published post

edit_post
DestructiveIdempotent

Update an already published post on Facebook, LinkedIn, X, Google Business, Telegram or YouTube. Preview the changes first and send them only after user approval.

Instructions

Change a post that is already live, in place. Facebook (Page posts), LinkedIn, X, Google Business, Telegram and YouTube. text is the new text (sent as each network's own field; YouTube: the description). Telegram also takes telegram_action: pin, unpin, stop_poll, edit_live_location, stop_live_location, and in params: telegram_reply_markup (buttons), telegram_parse_mode, telegram_link_preview, telegram_show_caption_above_media, telegram_pin_notify, telegram_media + telegram_media_type (replace the photo/video by URL or file_id), telegram_location. Google Business: the text plus call to action, event and offer fields in params (cta_type, cta_url, event_title, event_start_date, event_start_time, event_end_date, event_end_time, offer_coupon, offer_redeem_url, offer_terms); its media and schedule cannot be changed. Facebook: is_pinned, facebook_page_id. LinkedIn: linkedin_visibility, linkedin_disable_reshare. YouTube (post_id = video id), in params: title, tags, privacyStatus, categoryId, publishAt, defaultLanguage, localizations {lang: {title, description}}, localizations_remove, brand_partner (a UC… channel id), embeddable, publicStatsViewable, selfDeclaredMadeForKids, containsSyntheticMedia, license, recordingDate, paid_partnership; editing these spends about 51 units of the account's daily YouTube allowance. Instagram, TikTok and Threads posts cannot be edited. Needs the user's approval: call it first without confirmed to get a preview (nothing is sent), show the user exactly what will go out, and repeat the call with confirmed: true only after they approve.

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": {
      "user": "<user>",
      "platform": "<platform>",
      "post_id": "<post_id>"
    },
    "name": "edit_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
textNoNew text of the post (Telegram: text or caption).
userYesUpload-Post profile name.
paramsNoOther API fields for this action, with the REST API's own names (snake_case) and shapes. Per-network fields listed in the description. Leave out what you do not want to change.
post_idYesThe post id on the platform, as returned by the upload or get_media (Google Business: the full accounts/…/localPosts/… name).
platformYes
confirmedNoSet to true only after the user has seen the preview this tool returns without it and approved it. Without it nothing is sent.
telegram_actionNoTelegram only: an action on the message instead of (or with) a text change.

Output Schema

NameRequiredDescriptionDefault
resultNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. Addedv0.25.0

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already flag destructiveHint and openWorldHint, but the description adds material context they do not carry: editing sends nothing until `confirmed` is set (a two-step preview gate), YouTube field edits consume roughly 51 units of the daily allowance (a quota cost), and Google Business media/schedule are immutable. These are exactly the behavioral facts an agent needs before mutating live content.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Purpose and the confirmation protocol are front-loaded and no sentence is filler, but the body is one long run-on paragraph that packs dozens of per-network field names into a single sweep, which is hard to scan for a tool with six distinct platforms. The same content organized as short per-network groups would be materially easier to act on.

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?

For a destructive, multi-platform mutation tool with a nested free-form `params` object and 86% schema coverage, the description covers the platform matrix, immutable fields, per-network parameter names, quota cost, and the confirmation workflow. With an output schema present it needn't explain return values, so nothing an agent needs to call this correctly is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is already 86%, yet the description still adds substantial meaning: `text` is mapped per network (YouTube uses it as the description), `post_id` is identified as the video id on YouTube and the full localPosts name on Google Business, and the opaque `params` bag is enumerated per network (telegram_reply_markup, cta_type/event_*/offer_*, localizations, paid_partnership, etc.). The `confirmed` safety gate is also explained in behavioral terms, not just as a boolean.

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?

"Change a post that is already live, in place" gives a specific verb (change/edit), resource (published post), and the key scope constraint (already live, in place, not re-created). It then enumerates the six supported networks, so an agent can immediately separate this from edit_scheduled without opening either schema.

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?

The description states the supported platform set, explicitly names what is out of scope ("Instagram, TikTok and Threads posts cannot be edited"), and prescribes a concrete invocation protocol: call without `confirmed` for a preview, show the user what goes out, then repeat with `confirmed: true`. That is explicit when-to-use, when-not, and how-to-call, leaving nothing to inference.

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

Deploy Server

Other Tools