Skip to main content
Glama

Broadcast

by io.github.taraxe
OverviewDiscussionsAdmin

Validate a post

validate_post
Read-onlyIdempotent

Checks a post against every target network without creating anything: returns errors (blocking), warnings and the exact text each network would receive with its length. Call it before schedule_post when unsure whether a text, link or media fits every network; schedule_post runs the same checks and refuses an invalid post, but validate_post lets you fix it first with no side effect. Network rules (the server enforces them; use overrides for a shorter text on one network):

  • x: 280 chars (links count 23); Every link counts as 23 characters. Up to 4 images or 1 video.

  • bluesky: 300 chars; Up to 4 images or 1 video (50 MB max). Without media, the first link becomes a preview card.

  • facebook: 63206 chars; Published on the linked Facebook Page. Without media, the first link becomes a preview card.

  • instagram: 2200 chars; Media required: one image, a carousel (up to 10 images) or one video (Reel). Links in the caption are not clickable.

  • tiktok: 2200 chars; Media required: one video or a set of images. Links are not clickable; hashtags are recognised. Cannot be scheduled from the API: use status review, the user picks the TikTok settings in Broadcast.

  • linkedin: 3000 chars; Published on the linked personal profile. Up to 20 images or 1 video. Without media, the first link becomes an article card.

  • mastodon: 500 chars; Up to 4 images or 1 video.

  • threads: 500 chars; Emojis count as their UTF-8 bytes. Up to 20 images (JPEG or PNG) or 1 video (MP4 or MOV, 5 min max), at most 5 links. Without media, the first link becomes a preview card. Only the first hashtag becomes a topic. firstComment (optional) is posted as a reply under the post on x, bluesky, linkedin, threads, facebook and instagram, e.g. to keep a link out of a LinkedIn post; on X it costs credits like one more post. Dates are ISO 8601 with an offset; Europe/Paris is the user's time zone.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
bodyYesMain text of the post. Per-network overrides go in `overrides`.
linkNoLink appended after the text (becomes a preview card on Bluesky, Facebook and LinkedIn without media).
mediaNoImages (up to 10 for most networks) or one video. Not both.
repeatNoPublishes the post again every day, week or month at the same time (Europe/Paris), counted from scheduledAt: once an occurrence goes out, the next one is created with the same content. null stops the series. TikTok settings chosen in the app apply to every occurrence.
statusNodraft: saved without a date. review (default when scheduledAt is set): waits for an approval in the app. scheduled: published automatically at scheduledAt, without approval (needs the publish scope); with scheduledAt "now" it goes out within a minute.
accountsNoTarget account ids (see GET /accounts / list_accounts).
hashtagsNoHashtags appended on their own line, with or without the leading #.
overridesNoText replacing `body` for one network, keyed by account id or platform name (e.g. a shorter text for x).
platformsNoAlternative to `accounts`: every connected account of these networks.
scheduledAtNoISO 8601 date-time with offset (e.g. 2026-10-14T09:00:00+02:00), or "now". Required for status review and scheduled.
firstCommentNoOptional reply Broadcast posts under the post right after it goes out, from the same account (e.g. the link, kept out of the post on LinkedIn, or the rest of a thread). Only on x, bluesky, linkedin, threads, facebook and instagram; ignored elsewhere. Limits: 280 on x (links count 23), 300 on bluesky, 1250 elsewhere. On X it costs credits like one more post. If it fails, the post stays published and the target's comment.error says why.
idempotencyKeyNoClient-chosen key: a retried call with the same key returns the post already created instead of a duplicate.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changed
    • changedInput schema / properties / firstComment / description
      Previous value: -"Optional reply Broadcast posts under the post right after it goes out, from the same account (e.g. the link, kept out of the post on LinkedIn, or the rest of a thread). Only on x, bluesky and linkedin; ignored elsewhere. Limits: 280 on x (links count 23), 300 on bluesky, 1250 on linkedin. On X it costs credits like one more post. If it fails, the post stays published and the target's comment.error says why."New value: +"Optional reply Broadcast posts under the post right after it goes out, from the same account (e.g. the link, kept out of the post on LinkedIn, or the rest of a thread). Only on x, bluesky, linkedin, threads, facebook and instagram; ignored elsewhere. Limits: 280 on x (links count 23), 300 on bluesky, 1250 elsewhere. On X it costs credits like one more post. If it fails, the post stays published and the target's comment.error says why."
    • changedInput schema / properties / platforms / items / enum
      Previous value: -[
-  "bluesky",
-  "x",
-  "facebook",
-  "instagram",
-  "tiktok",
-  "linkedin",
-  "mastodon"
-]New value: +[
+  "bluesky",
+  "x",
+  "facebook",
+  "instagram",
+  "tiktok",
+  "linkedin",
+  "mastodon",
+  "threads"
+]
  2. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, and the description is fully consistent ('no side effect', 'without creating anything'). Beyond that it discloses the return content (blocking errors, warnings, the exact per-network text with its length), the server-enforced network rules, and how overrides interact with those rules — context the annotations do not carry.

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 highest-value content is front-loaded in the first two sentences (what it does, when to call it, why over schedule_post). The long per-network rules block is dense reference material that is justified given there is no output schema, though it makes the description heavy for a validation tool.

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?

There is no output schema, so the description carries the burden of explaining the return value — and it does, describing errors, warnings and the per-network rendered text with length. Combined with the network constraints and firstComment behavior, nothing an agent needs to call and interpret 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 100%, so the baseline is 3, but the description adds meaning the schema lacks: the per-network character/media rules that constrain body and media, the cross-parameter interaction of overrides ('a shorter text on one network'), the network whitelist for firstComment, and the timezone/offset requirement for dates.

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?

The first sentence gives a precise verb (checks/validates) and resource (a post against every target network) plus the crucial negative scope ('without creating anything'), and it explicitly contrasts with the sibling schedule_post. An agent can distinguish it from schedule_post, update_post and get_post without opening any 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?

It states the exact trigger ('call it before schedule_post when unsure whether a text, link or media fits'), names the alternative (schedule_post runs the same checks and refuses an invalid post), and explains the reason to prefer this one (fix it first with no side effect). When-to-use and when-to-use-the-alternative are both explicit.

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

All Broadcast 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