Skip to main content
Glama

generate_post

Generate AI-written posts for platforms by passing a theme. Get a post ID and status to track completion and schedule later.

Instructions

Generate AI content for a platform. Returns quickly with a postId and a 'generating' or 'completed' status — it does NOT block until generation fully finishes. Deducts 10 credits per variation. To control what the post is about, pass theme with a free-text brief (any topic/angle/facts/tone). If you omit theme, the topic is RANDOM — so always pass it when the user wants specific content. When variations > 1, ALL variations are returned under a SINGLE postId in the variations array — it does NOT create one post per variation. content is variation 1 (the primary, already saved on the post). Never call generate_post again to 'get the other variations' — they're all in the response. originalContent (if seen elsewhere) is the pre-voice-rewrite draft, not a separate variation. After generating, use create_post to save a chosen variation, then approve_post to schedule it. To repurpose: call repurpose_content first, then create_post with the result, then approve_post. Generation can take 1-5 minutes (longer with multiple variations or voice rewrite). This tool only waits a short grace period so fast generations can return inline content; if it returns status 'generating', the job is still running server-side — poll get_post with the returned postId until operationStatus is 'completed', then use that content. Do NOT call generate_post again for the same request while it's pending — retrying creates a duplicate draft and wastes credits. After generation, brand visual options (quote/card templates, brand images, stock photos) are prepared but NOT attached — share viewInBrowser for the visual picker, or call pick_post_visual to attach one. Do not attach a visual unless the user chooses it. The response includes editInVisualEditor: a direct URL to edit the post in the visual editor (once completed).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
themeNoFree-text topic/brief describing what the post should be about — include any angle, emphasis, key facts, or tone (e.g. "Launch announcement for our new MCP; emphasize NVIDIA + Stripe + Amotron; B2B authoritative tone"). ALWAYS pass this when the user wants the post to be about something specific. If omitted, a RANDOM brand theme is used and the topic will NOT match the user's request.
voiceNoVoice profile ID to apply
brandIdNoBrand ID (uses active brand if omitted)
themeIdNoOptional ID of a saved brand theme (from list_themes). Most callers should pass the free-text `theme` instead. If both are given, the free-text `theme` wins.
platformYesPlatform: x | linkedin | instagram | threads | facebook | custom:<charLimit>
variationsNoNumber of variations to generate
Behavior5/5

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

No annotations are present, so the description carries full burden. It thoroughly discloses non-blocking behavior, 10-credit deduction per variation, single postId for multiple variations, polling with get_post, duplicate-draft risk, and visuals not being attached automatically. This is exceptional transparency for a complex async tool.

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 description is lengthy but every sentence carries essential information—no fluff. It could be improved with bullet points or section headings, but the dense single-paragraph format is acceptable given the tool's complexity.

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 tool with 6 parameters, no output schema, and no annotations, the description is exceptionally complete. It covers async processing, credit costs, variation handling, post-save workflow, repurposing flow, visual options, and the editInVisualEditor URL—leaving very little unaddressed.

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 100%, setting a baseline of 3, but the description adds substantial meaning beyond the schema. It explains that omitting `theme` results in a random topic, that variations >1 all return under a single postId, and that free-text `theme` overrides `themeId` when both are given. This significantly enriches parameter understanding.

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 description opens with a clear verb+resource statement: 'Generate AI content for a platform.' It further distinguishes itself from sibling tools like generate_bulk_posts and generate_post_carousel by detailing single-post generation with variations and asynchronous return behavior.

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 workflow guidance is provided: 'After generating, use create_post to save a chosen variation, then approve_post to schedule it.' It also names alternatives (repurpose_content) and warns against repeated calls while pending, giving clear when-to-use and when-not-to-use context.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/bitsandtea/postking-mcp'

If you have feedback or need assistance with the MCP directory API, please join our Discord server