Skip to main content
Glama

Publish your own post to Instagram

publish_post
Destructive

Publish the user's own image(s) + caption to their connected Instagram account RIGHT NOW — story, feed post, or 2-10 image carousel. This is the free publishing surface: bring-your-own-content posts don't consume the monthly AI-story quota (a light daily anti-abuse bound applies). On the Free plan a short '✨ Posted with pith.day' line is appended to feed/carousel captions (the response's finalCaption shows exactly what was posted; Pro removes it). Stories publish the image as-is and Instagram ignores story captions. Requires a connected account (connect_instagram). Timeouts are safe: pass a random idempotency_key on the first call, and if the call times out, call again with the same key OR the returned draft_id — nothing double-posts. Scheduling is not supported here — posts go out immediately.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
handleNoInstagram handle (with or without @). Omit for your default account.
slidesNoCarousel slides (2-10), each with image_url or image_base64.
captionNoThe caption, verbatim (feed/carousel; stories ignore captions).
contextYesExplain why you are calling this tool and how it fits into the business owner's goal for their Instagram presence. This parameter is used for analytics and user intent tracking. YOU MUST provide 15-25 words (count carefully). NEVER use first person ('I', 'we', 'you') - maintain third-person perspective. NEVER include personal data, credentials, or the text of a draft. Example (20 words): "Reviewing the pending drafts before approving today's story, checking the caption matches the photo the owner expects."
draft_idNoResume a previous publish_post call: skips uploads, never double-posts.
image_urlNoPublic https image URL (story/feed). Exactly one of image_url/image_base64.
post_typeNoWhere to publish. Default feed.feed
image_base64NoRaw image bytes, base64-encoded, ≤8MB decoded (story/feed).
idempotency_keyNoRandom 8-64 char key (letters/digits/_/-). Reuse it on a timeout retry so the same post is resumed instead of re-created. Strongly recommended.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.8/5.0
Behavior5/5

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

Goes well beyond the annotations (which only flag destructive/openWorld). It discloses quota behavior, the Free-plan '✨ Posted with pith.day' caption watermark and how finalCaption reveals the exact posted text, that stories ignore captions, and the timeout/idempotency contract with draft_id resumption that prevents double-posting.

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?

It is long, but dense and front-loaded: the core action and modes come first, then constraints, then the idempotency contract. Nearly every sentence carries non-obvious operational information, though a few clauses (e.g. the anti-abuse bound) could be trimmed.

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 9-parameter mutation tool with no output schema and destructive/openWorld annotations, the description covers prerequisites, side effects, plan-dependent behavior, immediate-publish semantics, and safe-retry mechanics. An agent has everything needed to call it correctly.

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 already 100%, so the baseline is 3, but the description adds real operational meaning on top: how idempotency_key is reused on retry, and that draft_id resumes a prior call without double-posting. Remaining parameters (handle, slides, caption) get no extra guidance beyond the schema.

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 (publish), resource (the user's own image + caption), destination (connected Instagram account), and enumerates the supported modes (story, feed, 2-10 image carousel). It is clearly distinguishable from the sibling publish_draft, which handles generated drafts rather than bring-your-own content.

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?

Explicitly scopes usage: this is the free/own-content surface, requires a connected account via connect_instagram, and scheduling is explicitly not supported (posts go out immediately). It also names the alternative path implicitly by contrasting own-content posts with the draft flow.

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