Skip to main content
Glama

Generate images (server pipeline)

flypost_generate_image

Make an image for a concept with Flypost's AI image pipeline. variant: 'infographic' (classic), 'square' (clean square body for the canvas editor), 'single' (flat Image post: meme, stat, comparison or product). The only way to make meme, product_in_situ and 'Let AI decide' Image posts, or an AI image style the user asked for. It draws everything, so it cannot keep a real screenshot's pixels, and infographics and stat or comparison posts default to flypost_design_visual. Works on any concept-stage item. Blocks 2-6 minutes. Check the result with flypost_view_visuals, then give the user the editor_url. Stat and comparison images have no logo: place it with flypost_place_logo. Routes: flypost_guide (images).

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": {
      "content_bank_item_id": "<content_bank_item_id>",
      "variant": "<variant>"
    },
    "name": "flypost_generate_image"
  }
}

Input Schema

NameRequiredDescriptionDefault
variantYes
style_keyNoVisual style key; defaults to the item’s selected style.
aspect_ratioNoInfographic variant only; defaults to 'portrait 4:5' — LinkedIn's preferred shape. (square is forced 1:1; single images are always portrait.)
variation_countNo
content_bank_item_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.5/5.0
Behavior5/5

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

Beyond the annotations, the description discloses important behavior: the call blocks for 2-6 minutes, the pipeline redraws everything and cannot preserve real screenshot pixels, and stat/comparison images have no logo and require a separate flypost_place_logo step. It also tells the agent to verify with flypost_view_visuals and hand over editor_url, which is meaningful workflow context not present in structured fields.

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 front-loaded with purpose and then packs routing, constraints, and follow-up steps efficiently. It is dense and slightly wall-of-text, but nearly every sentence carries operational value; minor restructuring could improve scanability without adding content.

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 non-read-only generation tool with no output schema and five parameters, the description covers timing, limitations, verification, and downstream actions well. It is still missing how to obtain or interpret content_bank_item_id and style_key, which are required to invoke correctly, but otherwise gives an agent enough to use the tool safely.

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?

The description adds real meaning for the variant enum by explaining what 'infographic', 'square', and 'single' produce and which post types they support. However, with schema coverage at 40%, it leaves style_key and content_bank_item_id unexplained, and aspect_ratio/variation_count semantics remain mostly in the schema, so it only partially compensates for the coverage gap.

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 states a specific verb and resource ('Make an image for a concept with Flypost's AI image pipeline') and distinguishes behavior by variant. It also explicitly marks itself against flypost_design_visual for infographic/stat/comparison defaults, so an agent can tell which image-generation path to choose.

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 gives explicit when-to-use conditions: meme, product_in_situ, 'Let AI decide' Image posts, and user-requested AI image styles. It names the alternative path (flypost_design_visual), the verification tool (flypost_view_visuals), the follow-up logo tool (flypost_place_logo), and the guide route, leaving little inference required.

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.