Skip to main content
Glama

Revise a Designed layout with AI

flypost_revise_design

Change a Designed layout (carousel, infographic or Image post) by saying what should change, as the editor's "Revise with AI" does: the layout model revises the design as it is now, edits included, and leaves the rest alone. e.g. "make the 11% much bigger", "move the logos to the bottom", "change slide 3's headline to ...". One clear change per call works best. It comes back as a new version (an AI run on the user's image allowance); flypost_undo_design_revision brings the one before back. For an image post, pass draft_id when there is a post, so the image it shows is the one revised.

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>",
      "feedback": "<feedback>"
    },
    "name": "flypost_revise_design"
  }
}

Input Schema

NameRequiredDescriptionDefault
draft_idNoThe post, for an image post: its pinned image is the one revised.
feedbackYesWhat should change, in plain words.
content_bank_item_idYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.7/5.0
Behavior4/5

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

The annotations only cover the read-only/destructive/open-world profile; the description adds critical behavior beyond that: the result is a new version that consumes the user's AI image allowance, the rest of the layout is left alone, and an explicit undo sibling restores the prior version. It also clarifies the image-post path via draft_id. The only missing disclosure is failure behavior or limits beyond the allowance.

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 the purpose, then usage shape, then the new-version/allowance/undo behavior, then the image-post parameter hint. The examples are short and directly clarifying rather than filler. Slightly dense but every sentence contributes.

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 mutation tool with no output schema and only a partial annotation profile, the description covers what changes, what is preserved, what the result is, what it costs, how to undo it, and the image-post parameter nuance. It is not fully complete because the required content_bank_item_id remains unexplained and there is no note on invalid or empty feedback.

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 67%: feedback and draft_id are documented in the schema, and the description adds useful semantics for draft_id (pass it for an image post so its pinned image is the one revised) and for feedback (plain-words change description, one clear change). The required content_bank_item_id parameter has no description in either the schema or the description, leaving a meaningful gap.

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 states a specific verb and resource: change a Designed layout (carousel, infographic or Image post) by saying what should change, described as the editor's 'Revise with AI'. It distinguishes the operation from static editing by saying the layout model revises the design as it is now, but it does not explicitly name a sibling such as flypost_edit_slides to differentiate from.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It gives concrete usage guidance for invoking the tool: one clear change per call works best, and it names flypost_undo_design_revision as the revert path. However, it does not say when to use this rather than editing slides directly or regenerating a design, so the agent must infer the boundary from the sibling list.

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.