AXIS Avatar Foundry

Generate 3D Avatar from Image (Paid)

generate_avatar_from_image

PAID (x402, 6 USDC): generate a production 3D avatar from a reference photo (base64) — xAI A-pose normalize → TRELLIS.2 GPU mesh → full canonical post-process. Payment settles ONLY when generation completes; a failed generation is never charged. Returns a job_id — poll with the free get_generation_status tool (typical runtime 5-15 minutes). Pass idempotency_key when a retry is possible (timeout/5xx) — replaying the same key returns the original job_id instead of a second GPU job/charge. [Paid: $6.00 USDC via x402 for unauthenticated calls on the hosted /mcp endpoint; DEFERRED settlement — charged only when the generation job completes, a failed job is never charged. Poll get_generation_status (free).]

Input Schema

TableJSON Schema

Name	Required	Description
`prompt`	No	Optional style/subject hint alongside the image
`platform`	No	Target engine (adds rigging + engine export)
`image_b64`	Yes	Base64-encoded reference image (PNG/JPEG)
`asset_kind`	No	Asset taxonomy
`polygon_tier`	No	Quality tier (defaults to the platform's configured tier)
`texture_size`	No	Texture bake size in px (defaults per platform, else 2048)
`idempotency_key`	No	Optional caller-chosen dedup key (<=200 chars, [A-Za-z0-9_.:-]). Replaying the same key (per payer) returns the original job_id — no new GPU job, no new charge. Use on any retry after a timeout/5xx.

TDQS

A4.7/5.0

Behavior5/5

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

Annotations indicate a non-read-only, non-idempotent operation, but the description adds substantial detail: payment is settled only on completion, failed jobs are never charged, returns a job_id, and replaying idempotency_key returns the original job_id (no second charge). This goes well beyond annotations and discloses critical cost/behavior.

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

Conciseness3/5

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

The description is dense and includes redundant repetition (the bracketed cost/settlement note mirrors the opening). While front-loaded with key facts, it over-explains and could be tightened. Every sentence is informative, but the redundancy and length reduce conciseness.

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?

For a paid, async job tool, the description covers payment terms, job_id return, polling via get_generation_status, retry semantics, and typical runtime. No output schema exists, but the description explains what to expect. All necessary context for an agent to call and monitor the job is present.

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 parameters are already documented. The description adds meaningful semantics, particularly for idempotency_key (retry behavior, uniqueness per payer) and platform (adds rigging/export). It does not restate basic param meanings, but enriches them with usage context.

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 description clearly states the action: 'generate a production 3D avatar from a reference photo (base64)' and outlines the pipeline (xAI normalize → TRELLIS.2 → post-process). It distinguishes from the sibling generate_avatar_from_text by specifying photo input. No ambiguity about what the tool does.

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?

Explicitly explains when to use: for photo-based avatar generation. It names the free get_generation_status tool for polling and instructs to pass idempotency_key on retries after timeout/5xx. Though it does not mention 'when not to use' relative to text input, the photo-only scope is stated clearly, and the polling/retry guidance is actionable.

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 tools Inspect

Try in Browser

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A4/5.0

Disambiguation5/5

Each tool occupies a clearly distinct role: generation (image/text) plus status polling, pipeline processing (file vs inline), validation, repair, export, compliance, manifest verification, inspection, comparison, capabilities, and animation retargeting are all separated. The only potential overlap between axis_process and post_process_mesh is explicitly resolved by input method and scope.

Naming Consistency3/5

Two naming styles coexist: axis_* prefix for core pipeline/contract tools and descriptive non-prefixed names for generation, repair, and compliance tools. Within axis_*, the verb/noun order is inconsistent (e.g., axis_manifest_verify vs axis_list_capabilities), making the set readable but not uniform.

Tool Count5/5

14 tools is squarely within the ideal 3-15 range and matches the broad but well-defined scope of a full avatar foundry: generation, processing, validation, repair, export, compliance, and metadata inspection. Every tool serves a necessary function with no redundancy or bloat.

Completeness4/5

The toolset covers the full lifecycle from generation (image/text) and status polling through post-processing, repair, validation, export, and Roblox-specific compliance. Minor gaps exist, such as no tool to list available animation clips (retarget_animation references 'built-in' clips) or manage a library of previously generated avatars, but core workflows are fully supported.

Resources

Need Help?