Skip to main content
Glama

Build carousel PDF (server pipeline)

flypost_build_carousel

Render a carousel concept into its final PDF deck (1-4 minutes the user waits through). The PDF is only needed to publish: call this when the user wants the post scheduled or published, or asks for the PDF file. Never render to check your work or to show the deck: flypost_view_visuals shows every slide in seconds and the editor_url is the user's preview. It renders only what is stored on the item and does not make slide images (flypost_generate_slide_image does). A Designed layout deck already has its PDF: this returns it, re-rendering only if it was edited (free, no AI), and refuses template_family. Return the PDF url; do not download it. Required before scheduling a carousel post.

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>"
    },
    "name": "flypost_build_carousel"
  }
}

Input Schema

NameRequiredDescriptionDefault
image_densityNo
template_familyNoOmit to render the template already picked in the editor (the item's selected_style). Passing one also saves it as the item's template. Square 1080x1080: standard, editorial-light, minimal-ghost, minimal-marker, minimal-band. Tall 1080x1350: portrait-photo, photo-scrim, photo-split, photo-card, photo-poster. Wide 1920x1080: wide-cinema, wide-stage. standard/editorial-light/portrait-photo take ~22-30 words per slide. The minimal-*, photo-* and wide-* families expect one short statement per slide (~10-12 words), and photo-*/wide-* hook and body slides are built around a slide image, so generate those first with flypost_generate_slide_image. This call does not re-fit the copy to the template (the editor does that when the user switches template), so write the slides for the template you pass.
carousel_image_styleNo
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?

Goes well beyond the annotations: discloses a 1-4 minute latency the user must wait through, that a Designed layout deck returns its existing PDF and only re-renders if edited (free, no AI), that it refuses template_family in that case, and that the caller must not download the returned URL. These are non-obvious cost and failure behaviors that the readOnly/openWorld/destructive hints do not convey.

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-loads the action and latency, then routes to alternatives, then covers the Designed-layout edge case — a sensible priority order with no filler sentences. It is dense and clause-heavy with several parentheticals, which costs a point on readability but every sentence carries real information.

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?

No output schema exists, and the description compensates by stating the return value ('Return the PDF url; do not download it') along with latency, the re-render/reuse distinction, and the refusal case. The main gap is the two unexplained optional parameters (image_density, carousel_image_style) for a tool with four inputs.

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?

Schema coverage is only 25%, so the description must carry parameter meaning — and it does so thoroughly for template_family, adding family-to-aspect-ratio mapping, word-count expectations, and the crucial warning that copy is not re-fit to the passed template. However, image_density and carousel_image_style receive no mention at all in the description and no schema description, leaving two of four parameters undocumented anywhere.

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?

Opens with a specific verb+resource: 'Render a carousel concept into its final PDF deck,' and immediately distinguishes itself from image generation ('does not make slide images') and from preview tooling. An agent can tell this apart from flypost_generate_slide_image and flypost_view_visuals without reading either 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?

Gives an explicit trigger ('when the user wants the post scheduled or published, or asks for the PDF file'), explicit exclusions ('Never render to check your work or to show the deck'), and names the alternatives that serve those excluded cases (flypost_view_visuals, editor_url). It also states a hard precondition: 'Required before scheduling a carousel post.'

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.