dial-pptx-mcp

Overview Schema Source Related Servers Discussions Admin

render_svg_icon

Read-only

Convert your SVG line art into a PNG icon for PowerPoint slides, with an automated visual review that verifies the rendering is clean and readable before you place it.

Instructions

Render an SVG icon you have written to a PNG, and check it.

Use this when a slide needs an icon: call get_icon_guidance, write the SVG yourself following it, pass it here, and then place the returned icon_id with add_icon_to_slide. PowerPoint cannot embed SVG, which is why the rasterizing happens here rather than in your answer.

The icon is kept on the server, not in DIAL file storage, so the handle is all you need — and add_icon_to_slide is what places it, not add_image_from_dial_url (that tool reads DIAL storage, which is for images your image model generated).

The returned icon has been looked at. You cannot see what you drew, so the vision model is asked whether the render is free of artifacts and still readable at slide size. If "passed" is false, do not place the icon: fix the SVG as the issues say and call this again. An icon_id is returned only for an icon that is fit to use.

svg: the SVG source, self-contained line art — , , , , , . No text elements, no embedded images, no external references; a text label belongs in a textbox on the slide, not in the icon. concept: what the icon depicts ("supply chain", "regulatory approval"). Passed to the reviewer, which is the difference between "this is a clean pictogram" and "this reads as the thing you meant". size: longest side of the PNG in pixels (default 800). An icon is displayed at about an inch, so this is deliberate headroom; there is no reason to raise it. background: the icon's own background. Leave "transparent" — that is the whole advantage over a stock icon, and it is what lets the same icon sit on a white slide and on a brand-coloured panel. A hex colour bakes a solid rectangle in behind it. slide_background: hex colour of the surface the icon will sit on. The review judges legibility and contrast against it, so set it to the panel colour for an icon going on a coloured card. review: set false only to skip the vision check (faster, unverified).

Returns "icon_id" (pass it straight to add_icon_to_slide), the pixel size, and "review" with the verdict and any issues. The handle stays valid for the session, so reuse it wherever the icon repeats instead of rendering the same drawing again.

Input Schema

TableJSON Schema

Name	Required	Default
`svg`	Yes
`size`	No
`review`	No
`concept`	No
`background`	No	transparent
`slide_background`	No	#FFFFFF

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

Addedv2.8.0Sep 9, 2026

TDQS

A4.2/5.0

Behavior1/5

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

The description explicitly says 'The icon is kept on the server' and 'The handle stays valid for the session', indicating that calling the tool creates and retains server-side state. The annotations declare readOnlyHint: true, which claims the tool does not modify state, so the description contradicts the annotation.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is long but tightly organized: a front-loaded summary, then workflow and storage context, then failure behavior, then parameter-by-parameter explanations. Each sentence adds operational value, and important warnings are bolded.

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?

It covers the full calling sequence, the return contract (icon_id, review verdict, issues), failure handling ('if passed is false, do not place the icon'), and reuse guidance. It even explains why rasterization is necessary, so an agent can predict behavior in the surrounding workflow.

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

Parameters5/5

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

Schema description coverage is 0%, but the description compensates with detailed per-parameter guidance: svg constraints (no text/images/external refs), concept's role in the reviewer, size rationale, transparent background advantage, slide_background for contrast, and review's skip semantics. This is far beyond what the bare schema offers.

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 first sentence states a specific action ('Render ... to a PNG') and resource (SVG icon), and the surrounding text distinguishes it from add_icon_to_slide and add_image_from_dial_url. It is immediately clear what this tool does and where it fits in the slide-assembly pipeline.

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 an explicit workflow: when a slide needs an icon, call get_icon_guidance, write the SVG, pass it here, then place the result with add_icon_to_slide. It also says add_image_from_dial_url is the wrong alternative and tells when review can be skipped, leaving no ambiguity about when to use this tool.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server