Skip to main content
Glama

Change a post

update_post
Destructive

Change a post's words, hashtags, link, day, time, its picture or video (from the Library), or the angle its words take. Send only what changes. Returns the post with schedule_check: what Schedule would decide now. A post already scheduled can be changed only with the schedule permission; one already handed to its platform's own schedule (Facebook, YouTube) or one that went out cannot be changed here.

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": {
      "post_id": "<post_id>"
    },
    "name": "update_post"
  }
}

Input Schema

NameRequiredDescriptionDefault
dateNoThe day it goes out, YYYY-MM-DD, inside the campaign's window. A draft may be saved with a day gone by; Schedule asks for one still ahead (schedule_check says so).
testNoThe test this post is a variant of, or null to take it out: collab_starter (artist or audora: Who starts the Collab: the artist's post with Audora invited, or Audora's post with the artist invited). Audora pools each variant's posts at day 7 and calls the test once each variant has enough posts and one is clearly ahead; Admin shows the reading.
timeNoThe time it goes out, HH:MM 24-hour, in the artist's own time zone.
angleNoWhich of Audora's post angles the words take (the key names it: listener_pov is the listener's side of the song, tail_section a part of the track no other post used, hook_object an object the song names, and so on). Audora counts how each angle does for the artist, and promo_results' what_works shows the result. get_campaign shows each post's angle.
artistNoOnly when you are connected as a label: the roster artist this call is for — their artist_user_id from list_roster, or their exact artist name. Required for every artist tool on a label connection. Leave it out on an artist's own connection.
captionNoThe words of the post, as they will be published. The lane's limit and Audora's text rules apply (no placeholders, nothing that points back at another post).
dry_runNoTrue to check the call and see what it would do, without writing anything.
post_idYesThe post's id (post_id from get_campaign or promo_this_week).
hashtagsNoUp to 12 hashtags, with or without #. Replaces the list.
link_urlNoA web address the post links to, or null to remove it.
media_asset_idNoA picture (for a picture post) or a video (for a video post) already in the artist's Library, by its media asset id. Audora does not make pictures or videos through this connection.
idempotency_keyNoSend the same key if you retry, and the change happens once.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • addedInput schema / properties / test
      Added value: +{
      +  "description": "The test this post is a variant of, or null to take it out: collab_starter (artist or audora: Who starts the Collab: the artist's post with Audora invited, or Audora's post with the artist invited). Audora pools each variant's posts at day 7 and calls the test once each variant has enough posts and one is clearly ahead; Admin shows the reading.",
      +  "properties": {
      +    "test": {
      +      "enum": [
      +        "collab_starter",
      +        "sound",
      +        "format"
      +      ],
      +      "type": "string"
      +    },
      +    "variant": {
      +      "enum": [
      +        "artist",
      +        "audora",
      +        "official",
      +        "baked",
      +        "silent",
      +        "reel",
      +        "carousel"
      +      ],
      +      "type": "string"
      +    }
      +  },
      +  "required": [
      +    "test",
      +    "variant"
      +  ],
      +  "type": [
      +    "object",
      +    "null"
      +  ]
      +}
  2. Changed1 schema field changed
    • changedInput schema / properties / date / description
      Previous value: -"The day it goes out, YYYY-MM-DD, inside the campaign's window and not in the past."New value: +"The day it goes out, YYYY-MM-DD, inside the campaign's window. A draft may be saved with a day gone by; Schedule asks for one still ahead (schedule_check says so)."
  3. Changed1 schema field changed
    • changedInput schema / properties / angle / enum
      Previous value: -[
      -  "pin_angle.hook_object",
      -  "pin_angle.listener_pov",
      -  "pin_angle.lyric_line_on_beat",
      -  "pin_angle.occasion_day",
      -  "pin_angle.one_answerable_question",
      -  "pin_angle.ordinary_scene_contrast",
      -  "pin_angle.place_light_and_weather",
      -  "pin_angle.place_named_in_words",
      -  "pin_angle.release_fact_card",
      -  "pin_angle.repeat_what_worked",
      -  "pin_angle.scene_vocabulary",
      -  "pin_angle.story_line_that_nearly_went",
      -  "pin_angle.story_place",
      -  "pin_angle.tail_section",
      -  "pin_angle.uploaded_asset_hero"
      -]New value: +[
      +  "pin_angle.hook_object",
      +  "pin_angle.listener_pov",
      +  "pin_angle.lyric_line_on_beat",
      +  "pin_angle.occasion_day",
      +  "pin_angle.one_answerable_question",
      +  "pin_angle.ordinary_scene_contrast",
      +  "pin_angle.place_light_and_weather",
      +  "pin_angle.place_named_in_words",
      +  "pin_angle.release_fact_card",
      +  "pin_angle.repeat_what_worked",
      +  "pin_angle.scene_vocabulary",
      +  "pin_angle.show_coming_up",
      +  "pin_angle.story_line_that_nearly_went",
      +  "pin_angle.story_place",
      +  "pin_angle.tail_section",
      +  "pin_angle.uploaded_asset_hero"
      +]
  4. Changed1 schema field changed
    • addedInput schema / properties / angle
      Added value: +{
      +  "description": "Which of Audora's post angles the words take (the key names it: listener_pov is the listener's side of the song, tail_section a part of the track no other post used, hook_object an object the song names, and so on). Audora counts how each angle does for the artist, and promo_results' what_works shows the result. get_campaign shows each post's angle.",
      +  "enum": [
      +    "pin_angle.hook_object",
      +    "pin_angle.listener_pov",
      +    "pin_angle.lyric_line_on_beat",
      +    "pin_angle.occasion_day",
      +    "pin_angle.one_answerable_question",
      +    "pin_angle.ordinary_scene_contrast",
      +    "pin_angle.place_light_and_weather",
      +    "pin_angle.place_named_in_words",
      +    "pin_angle.release_fact_card",
      +    "pin_angle.repeat_what_worked",
      +    "pin_angle.scene_vocabulary",
      +    "pin_angle.story_line_that_nearly_went",
      +    "pin_angle.story_place",
      +    "pin_angle.tail_section",
      +    "pin_angle.uploaded_asset_hero"
      +  ],
      +  "type": "string"
      +}
  5. First observed

TDQS

A4.1/5.0
Behavior4/5

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

Annotations already flag destructiveHint=true and readOnlyHint=false, but the description adds information annotations cannot carry: the permission gate for scheduled posts, the hard exclusion for platform-scheduled/published posts, and the fact that the response includes a schedule_check of what Schedule would decide. That is genuinely decision-relevant behavior for a destructive mutation.

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-loaded with the capability list, then the partial-send rule, then the return value, then the eligibility caveats. Dense but every sentence carries operative information; the final sentence is long but packs three distinct exclusion rules.

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 12-parameter mutation with no output schema, the description covers what changes, how to send changes, what comes back (schedule_check), and the full set of blocking conditions. No output schema is needed because the return surface is described inline.

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 the baseline is 3, but the description adds the crucial partial-update contract ('Send only what changes') that the 12-param schema itself does not state, plus the constraint that media must come from the existing Library and cannot be created here. It omits per-parameter detail, which is acceptable given the schema's depth.

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?

Opens with a specific verb+resource ('Change a post') and enumerates the mutable surface: words, hashtags, link, day, time, picture/video, angle. An agent can tell this is a partial-update tool versus add_post/create tools, though no sibling is named explicitly and the distinction is inferred from the tool name rather than the description.

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?

Explicit when-not guidance: posts already handed to a platform's own scheduler (Facebook, YouTube) or already published cannot be changed here, and scheduled posts require the schedule permission. 'Send only what changes' sets the intended call pattern. It stops short of naming a concrete alternative tool for the excluded cases, so it is strong context rather than a full routing rule.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources