Skip to main content
Glama

Generate article cover (server pipeline)

flypost_generate_article_cover

Make the cover image (16:9, 1070x607) for a Pulse article, two ways. By default an AI image model paints it in a carousel illustration style. With from_article_assets: true no AI runs and nothing is charged: the cover is the article's headline in the brand's fonts and colours next to the real logos of the tools the article names (a roundup's entries: each logo comes from Flypost's logo library, else from the tool's own website, and is composited as the real file, never redrawn). Use it for roundups and comparisons ('I tested 8 X alternatives'); it needs at least two named tools with a logo, and fails otherwise. The same logos and the article's homepage screenshots are then also offered as movable images in the app's cover editor. Blocks until ready (typically 1-3 minutes). Returns editor_url: hand it to the user so they can see the cover in place on the article.

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": {
      "article_id": "<article_id>"
    },
    "name": "flypost_generate_article_cover"
  }
}

Input Schema

NameRequiredDescriptionDefault
styleNoCarousel illustration style key for an AI cover. Ignored with from_article_assets.
article_idYes
from_article_assetsNotrue = build the cover from the article's own assets (headline + the named tools' real logos), no AI. Default false.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A4.2/5.0
Behavior4/5

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

Annotations only declare non-read-only, non-destructive, closed-world; the description adds far more: cost behavior per mode ('nothing is charged'), a failure condition, a blocking latency estimate ('typically 1-3 minutes'), and a side effect (logos and homepage screenshots appear as movable images in the app's cover editor). The one gap is that it doesn't say what happens to an existing cover when regenerating, which matters for a mutation 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?

Front-loaded with output format and the default-vs-opt-in split, then cost, then failure, then return value – a sensible priority order. It is dense with nested parentheticals and asides (logo sourcing, cover-editor side effect) that could be split or trimmed, but no sentence is pure filler.

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?

With no output schema, the description still tells the agent what comes back ('Returns editor_url: hand it to the user') and what to do with it. For a long-running, billable generation tool with only three params, it covers cost, latency, failure, and downstream side effects – everything needed to call it correctly and set expectations.

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?

At 67% schema coverage the schema already documents style and from_article_assets, and the description largely restates them (AI style key, ignored with from_article_assets; asset mode = headline + real logos). It adds the practical consequence of from_article_assets (no AI, no charge, real files never redrawn) but says nothing about article_id beyond the obvious, and gives no example values or constraints for style.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a concrete verb and resource ('Make the cover image (16:9, 1070x607) for a Pulse article') and clearly separates two operating modes (AI-painted vs. asset-composited). It never names a sibling tool (e.g. flypost_generate_image or flypost_generate_slide_image) to contrast with, so an agent must infer the boundary from context rather than being told.

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 positive case explicitly ('Use it for roundups and comparisons ("I tested 8 X alternatives")') and the precondition ('needs at least two named tools with a logo, and fails otherwise'). The mode switch is spelled out with the exact flag ('With from_article_assets: true no AI runs'), leaving nothing to infer.

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.