Skip to main content
Glama
Brilliant MCP

Brilliant MCP

Official

generate_svg

Create editable SVG icons, logos, illustrations, and diagrams from text prompts, placing them on the canvas as native shapes for scalable, easily modified designs.

Instructions

Generate editable vector graphics (SVG) from a text prompt and place them on the canvas as native editable shapes. Use for icons, logos, illustrations, diagrams — anything that should stay crisp and remain editable. For photos / realistic images use generate_image instead. Optional referenceElementIds (up to 4) export to PNG and steer style. Use n (1–4) for parallel variations of a single prompt, or targets to fan out distinct prompts in parallel. Call get_knowledge(["svg/prompts","svg/integration"]) for prompt patterns and decision rules. Requires Quiver API key.

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": {
      "canvasId": "<canvasId>"
    },
    "name": "generate_svg"
  }
}

Input Schema

NameRequiredDescriptionDefault
nNoNumber of variations from the single prompt (1–4, default 1). Cheaper than `targets` because it is one API call.
intentNoA short present-tense line shown beside your cursor while the vector is drawn, e.g. 'Sketching a fox logo'. Optional; derived from the prompt when absent.
promptNoNatural-language description of the SVG to generate.
targetsNoBatch mode: distinct prompts generated in parallel. Use for multiple different SVGs (e.g. "search icon", "settings icon").
canvasIdYesCanvas ID. Required.
sessionIdNoSession ID for per-session visual feedback. Optional.
instructionsNoOptional style/behavior instructions for the model.
referenceElementIdsNoElement IDs to export as PNG and pass as style references (up to 4).

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.10

TDQS

A4.7/5.0
Behavior5/5

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

Beyond the annotations (which only convey non-read-only, open-world, non-idempotent, non-destructive), it discloses the Quiver API key prerequisite, that `referenceElementIds` triggers a PNG export as a side effect, and that `n` is cheaper than `targets` because it is a single API call. These are cost/prerequisite facts an agent cannot get from 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?

Front-loaded with the core action and effect, then alternatives, then parameter nuances, then prerequisites — no filler sentences. It is denser and longer than ideal, and the get_knowledge pointer sits mid-block rather than with the other prerequisites, slightly muddying the structure.

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?

With 8 parameters and no output schema, the description covers purpose, alternatives, prerequisites, and the two non-obvious parameters well. The one remaining gap is return value — it never says whether element IDs or a result payload come back after placement — which matters more because no output schema exists.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is 3; the description still adds real meaning by explaining the `n` vs `targets` trade-off (cost, one call vs parallel fan-out) and the 4-reference cap and styling role of `referenceElementIds`. It leaves `intent`, `instructions`, and `sessionId` to the schema, which is acceptable given full coverage.

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?

States a specific verb and resource ('Generate editable vector graphics (SVG) from a text prompt') plus the effect ('place them on the canvas as native editable shapes'). It names the use cases (icons, logos, illustrations, diagrams) and explicitly contrasts with the sibling `generate_image`, so an agent can route without opening 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?

Explicit when-to-use ('anything that should stay crisp and remain editable') and when-not ('For photos / realistic images use `generate_image` instead'), plus a routing rule for guidance content via get_knowledge(["svg/prompts","svg/integration"]). It also disambiguates the two batch shapes: `n` for variations of one prompt vs `targets` for distinct prompts.

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