Skip to main content
Glama

AXIS Avatar Foundry

by com.jonathanarvay
OverviewDiscussionsAdmin

Post-Process Generated Mesh (Inline GLB or URL)

post_process_mesh
Read-onlyIdempotent

Post-process a RAW generated mesh (normalize → mesh-repair → rig/skin → validate → export) and return the finished, validated GLB as base64. The inline counterpart of axis_process (which needs a server file path) — the generation post-process step, callable by an LLM/agent that holds the mesh bytes (e.g. fresh TRELLIS output) or a URL to them. Provide the mesh EXACTLY one of two ways: inline as base64 (glb_base64) or as an HTTPS URL (mesh_url) — the URL's host must be on this server's operator-configured allowlist (off by default; an unconfigured allowlist refuses every mesh_url call, it is never open to an arbitrary host). Providing both or neither is a real input error. [Paid: $1.50 USDC via x402 for unauthenticated calls on the hosted /mcp endpoint; settled only on a successful (non-error) result.]

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
mesh_urlNoHTTPS URL to fetch the raw GLB from instead of inline base64 (e.g. a presigned storage URL) — the host must be on this server's configured allowlist (off by default). Provide exactly one of glb_base64 or mesh_url.
platformNoTarget engine platform (adds export validation)
asset_kindNoAsset kind (skinning auto-on for avatar only)
glb_base64NoBase64-encoded raw binary GLB to post-process. Provide exactly one of glb_base64 or mesh_url.
polygon_tierNoDecimation tier for the output mesh
run_skinningNoOverride skinning (default: avatars only)

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / asset_kind / enum
      Previous value: -[
-  "avatar",
-  "prop",
-  "vehicle",
-  "environment",
-  "vfx",
-  "weapon_armor",
-  "character_accessory",
-  "generic"
-]New value: +[
+  "avatar",
+  "prop",
+  "vehicle",
+  "environment",
+  "creature",
+  "weapon_armor",
+  "character_accessory",
+  "generic"
+]
  2. Changed3 schema fields changed
    • changedInput schema / properties / glb_base64 / description
      Previous value: -"Base64-encoded raw binary GLB to post-process"New value: +"Base64-encoded raw binary GLB to post-process. Provide exactly one of glb_base64 or mesh_url."
    • addedInput schema / properties / mesh_url
      Added value: +{
+  "description": "HTTPS URL to fetch the raw GLB from instead of inline base64 (e.g. a presigned storage URL) — the host must be on this server's configured allowlist (off by default). Provide exactly one of glb_base64 or mesh_url.",
+  "type": "string"
+}
    • removedInput schema / required
      Removed value: -[
-  "glb_base64"
-]
  3. First observed

TDQS

A4.6/5.0
Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, and the description goes well beyond them: the allowlist gating for mesh_url (off by default, refuses every call when unconfigured, never open to arbitrary hosts), the $1.50 USDC x402 charge for unauthenticated calls on the hosted endpoint, and that settlement only occurs on a successful result. That is exactly the kind of auth/cost/failure context annotations cannot 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-loaded with the verb, the pipeline, and the return value, then the routing distinction, then the input rule. Dense parenthetical asides (the TRELLIS example, the allowlist caveat, the pricing bracket) add length, but each carries real information rather than filler.

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?

No output schema exists, so the description correctly specifies the return (base64 GLB) and the validation guarantee. It also compensates for the zero-required-parameter schema by stating the one-of-two input requirement, and covers cost, auth, and allowlist prerequisites an agent needs before calling.

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 description coverage is 100%, so the schema already documents every parameter, including the glb_base64/mesh_url exclusivity and the avatar-only skinning default. The description reinforces the XOR rule and adds the error consequence, but contributes no new syntax or format detail beyond the schema. Baseline 3 applies.

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+resource (post-process a RAW generated mesh) and enumerates the pipeline stages (normalize → mesh-repair → rig/skin → validate → export), plus states the exact output (validated GLB as base64). It explicitly distinguishes itself from the closest sibling, axis_process, by noting that one needs a server file path while this one takes inline bytes or a URL.

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 when-to-use condition (the agent holds the mesh bytes, e.g. fresh TRELLIS output, or a URL to them) and names the alternative (axis_process) with the condition that selects it. It also states the input exclusivity rule and its consequence: providing both or neither is a real input error.

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

All AXIS Avatar Foundry toolsInspect
Try in Browser
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

Resources