Skip to main content
Glama

Create an AI image for a text post

flypost_create_post_image

Give a TEXT post an AI-made picture (the app's "Create an image with AI") from an idea the user picked: one of yours (a short title, 1-2 sentences on what is in the frame, on_image_text of at most 6 words) or one from flypost_suggest_post_image_ideas. Only after the user has chosen: it costs from their image allowance. Adds the picture to the post's photos; usually under a minute. Rules for ideas: concrete and drawable, tied to this post, never a real product's UI or logo, no brand name, and the words on the image never claim more than the post does (a post that says 'reportedly' gets no image stating it as fact). Not for image, infographic or carousel posts (flypost_design_visual), or an image the user supplied (flypost_attach_post_image).

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": {
      "draft_id": "<draft_id>",
      "idea": "<idea>"
    },
    "name": "flypost_create_post_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
ideaYesThe idea the user picked. on_image_text is the ONLY text drawn: the post's most striking point in 3-10 words. Always include it; a wordless picture says nothing in the feed.
draft_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.3/5.0
Behavior4/5

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

Annotations only declare the generic safety profile (readOnlyHint=false, destructiveHint=false, openWorldHint=false); the description adds real behavioral context the agent cannot get from annotations — it consumes the user's image allowance, mutates the post by appending to its photos, and typically completes in under a minute. It also surfaces non-obvious content constraints (no real product UI or logos, no brand names, words on image must not overclaim relative to the post). It stops short of describing what is returned on success/failure or whether repeated calls attach multiple images.

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 core action, the precondition, and the cost are front-loaded in the first two sentences, and the exclusions close the paragraph usefully. The middle 'Rules for ideas' run-on and the nested parenthetical listing the idea fields are dense, but each clause carries operational content rather than repetition.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a mutating, cost-bearing, nested-parameter tool with no output schema, the definition covers the important operational facts: prerequisite user selection, allowance consumption, side effect on the post's photos, and latency. The gaps are the return value (no output schema and no mention of what comes back) and the unresolved word-count/element-requirement mismatch between description and schema for on_image_text.

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

Parameters3/5

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

With 50% schema coverage and draft_id undocumented in the schema, the description does compensate by explaining the shape of the nested idea object: a short title, 1-2 sentences describing the frame, and on_image_text. However, it introduces a direct conflict on that last field — the description caps it at 'at most 6 words' while the schema says 'the post's most striking point in 3-10 words' and 'Always include it' (the schema also lists only title and description as required). The agent is left unsure which limit governs, so the added meaning partly undercuts itself.

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 specific verb+resource+target: giving a TEXT post an AI-made picture from a chosen idea. It explicitly distinguishes itself from three siblings (flypost_suggest_post_image_ideas for ideas, flypost_design_visual for image/infographic/carousel posts, flypost_attach_post_image for user-supplied images), so an agent can route correctly 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 precondition plainly ('Only after the user has chosen'), names the two legitimate idea sources, and lists explicit exclusions with the sibling that handles each excluded case. When-to-use, when-not-to-use, and alternatives are all present.

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.