Skip to main content
Glama

AI PBR Material Generator

generate_pbr_material
Idempotent

Seamless PBR material from a text prompt: albedo (base color), normal, roughness and height maps. Realistic or stylized. Precise layouts (herringbone, chevron, Versailles parquet, basket weave, hexagon tiles...) are drawn exactly so they tile. Asynchronous: returns a generation id; poll get_generation. Spends credits (refunded automatically on failure). Typical time: 120 s.

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": {
      "prompt": "<prompt>",
      "max_credits": "<max_credits>"
    },
    "name": "generate_pbr_material"
  }
}

Input Schema

NameRequiredDescriptionDefault
modelNotexel-quality = best (1K / 2K / 4K), texel-express = fastest and cheapest (1K only: any other resolution is delivered and charged in 1K), texel-classic = alternative look (1K / 2K / 4K). The 4K is native.texel-quality
styleNorealistic
promptYesMaterial description, e.g. "mossy medieval cobblestone, wet".
resolutionNo4k_native is accepted as 4k (the 4K is native). texel-express always runs in 1K.4k
max_creditsYesHighest price the user accepted (from quote_generation). The call fails with confirmation_required if missing.
output_formatNopng
idempotency_keyNoOptional. Same key = same generation, never charged twice. Default: derived from the parameters for 10 minutes; pass a new value to intentionally run the same prompt again.
save_to_libraryNoOptional. When the generation succeeds, publish it in the public 3DTexel community library and add it to the user's library (free). Only if the user asked for it.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed4 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"texel-quality = best (2K / native 4K), texel-classic = alternative look (2K / native 4K)."New value: +"texel-quality = best (1K / 2K / 4K), texel-express = fastest and cheapest (1K only: any other resolution is delivered and charged in 1K), texel-classic = alternative look (1K / 2K / 4K). The 4K is native."
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "texel-quality",
      -  "texel-classic"
      -]New value: +[
      +  "texel-quality",
      +  "texel-express",
      +  "texel-classic"
      +]
    • addedInput schema / properties / resolution / description
      Added value: +"4k_native is accepted as 4k (the 4K is native). texel-express always runs in 1K."
    • changedInput schema / properties / resolution / enum
      Previous value: -[
      -  "2k",
      -  "4k",
      -  "4k_native"
      -]New value: +[
      +  "1k",
      +  "2k",
      +  "4k",
      +  "4k_native"
      +]
  2. Changed2 schema fields changed
    • changedInput schema / properties / model / description
      Previous value: -"texel-quality = best (2K / native 4K), texel-express = fastest (2K max, 4K requests are made in 2K), texel-classic = alternative look (2K / native 4K)."New value: +"texel-quality = best (2K / native 4K), texel-classic = alternative look (2K / native 4K)."
    • changedInput schema / properties / model / enum
      Previous value: -[
      -  "texel-quality",
      -  "texel-express",
      -  "texel-classic"
      -]New value: +[
      +  "texel-quality",
      +  "texel-classic"
      +]
  3. Changed1 schema field changed
    • changedInput schema / properties / model / description
      Previous value: -"texel-quality = best (2K / native 4K), texel-express = fastest (2K max), texel-classic = alternative look (2K / native 4K)."New value: +"texel-quality = best (2K / native 4K), texel-express = fastest (2K max, 4K requests are made in 2K), texel-classic = alternative look (2K / native 4K)."
  4. Changed1 schema field changed
    • changedInput schema / properties / model / description
      Previous value: -"texel-quality = best (2K/4K/4K native), texel-express = fastest (2K/4K), texel-classic = alternative look."New value: +"texel-quality = best (2K / native 4K), texel-express = fastest (2K max), texel-classic = alternative look (2K / native 4K)."
  5. Changed1 schema field changed
    • removedInput schema / properties / enhance_seamless
      Removed value: -{
      -  "default": false,
      -  "description": "Beta: second AI pass that repaints the edges (+5 to +10 credits, about 1 minute longer).",
      -  "type": "boolean"
      -}
  6. First observed

TDQS

A4.4/5.0
Behavior5/5

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

Goes well beyond the annotations (which only declare readOnly=false, openWorld=true, idempotent=true, destructive=false) by disclosing the async lifecycle ('returns a generation id; poll get_generation'), the credit spend with automatic refund on failure, and a ~120 s typical runtime. These are exactly the operational facts an agent needs before committing to a long, paid call.

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?

Four tight sentences, front-loaded with what is produced, then tiling behavior, then the async/cost/time contract. Every sentence carries distinct, decision-relevant information with no padding.

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 no output schema, the description appropriately explains the return contract (a generation id to poll via get_generation) and the cost/timing profile. The quote_generation prerequisite for max_credits is only surfaced in the schema, but overall the definition is complete enough to invoke correctly.

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 75%, so the schema already documents most parameters including model tiers, resolution, max_credits, idempotency_key and save_to_library. The description adds only marginal parameter meaning — the output map list and the 'realistic or stylized' framing that maps to the style enum — leaving the schema to carry the rest.

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?

Names a specific verb and resource ('Seamless PBR material from a text prompt') and enumerates the outputs (albedo, normal, roughness, height maps), which cleanly separates it from siblings like generate_texture, generate_hdri and generate_3d_model. An agent can identify the tool without opening the schema.

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

Usage Guidelines4/5

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

Gives real selection context: realistic vs stylized, precise tileable layouts (herringbone, chevron, parquet) that 'are drawn exactly so they tile', plus the async workflow (poll get_generation). It does not explicitly contrast with the sibling generators or state when NOT to use it, so it stops short of full routing guidance.

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.