Gradient Dynamics: thermal and CFD simulation

Preview a design

create_design_preview

Idempotent

Create a template concept and display it in interactive 3D. Preferred for a quick initial design: creates a project if omitted, submits one durable geometry job and waits briefly for its viewer. No account check or full catalogue scan needed. For an unspecified GPU cold-plate concept use cold_plate; it is a simple parallel-channel concept, not a verified GPU package layout. Preserve explicit requirements; use get_template for customised parameters. Reuse the same key/arguments on network retry. Pending results continue with get_design_preview. This creates geometry only, with no mesh or simulation.

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": {
      "idempotency_key": "<idempotency_key>"
    },
    "name": "create_design_preview"
  }
}

Input Schema

Name	Required	Description	Default
`name`	No		Concept design
`method`	No	Exact STEP by default. For purpose=meshing, auto permits checked faceted STEP for implicit volumes; artifacts record the actual representation.	exact
`outputs`	No
`purpose`	No	Meshing requires explicit volume output_names; heatmaps, boundary patches and display helpers are rejected by the geometry engine.	export
`bounds_m`	No
`document`	No	Self-contained gd.design/v1 feature graph, up to 1 MiB. Use native design catalogue/edit operations to compose it. Mutually exclusive with template_id; assets/external references are not supported. Native validity, manufacturing and exact export are checked by the worker.
`named_stl`	No	Also export each selected document body as a separate named STL, alongside the combined surface, for mesh wall patches.
`parameters`	No
`project_id`	No
`resolution`	No
`template_id`	No	Registered template; mutually exclusive with document
`output_names`	No
`wait_seconds`	No
`deflection_mm`	No
`workflow_name`	No
`idempotency_key`	Yes	Use a fresh unique key for each newly requested job, even with identical inputs or a matching completed job. Reuse unchanged only for retries/resuming that same intended job. Never replace it to retry an uncertain submission.
`design_brief_artifact_id`	No	Immutable owned design brief used to derive this candidate; retained in job lineage

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.6/5.0

Behavior5/5

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

Beyond the annotations (which only declare idempotent, non-destructive, open-world), the description discloses job lifecycle behavior: it creates a project if one is omitted, submits a single durable geometry job, waits briefly for the viewer, and continues asynchronously via get_design_preview. It also states retry semantics (reuse the same key/arguments on network retry) and the output boundary (geometry only, no mesh or simulation), which is exactly the context an agent can't get from the annotations alone.

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?

Front-loaded with the core action and preference, then layered with alternatives, retry guidance, and scope limits, all in compact sentences that each add a distinct fact. No filler or restatement of the title.

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?

For a 17-parameter job-submitting tool with an output schema, the description covers lifecycle, waiting, continuation, retry, and output boundaries well, so return-value explanation is not needed. The remaining shortfall is parameter-level detail, which the schema only partially supplies.

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 only 41% across 17 parameters, so the description must carry more weight; it clarifies idempotency_key retry semantics, project_id auto-creation, and the template/concept nature of the call. However, it leaves resolution, deflection_mm, outputs, output_names, named_stl, bounds_m, method, workflow_name, and design_brief_artifact_id unexplained, so many parameters are documented only by terse or absent schema text.

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 ('Create a template concept and display it in interactive 3D') and immediately bounds scope ('creates geometry only, with no mesh or simulation'), which separates it from create_mesh, create_geometry, and get_design_preview. The agent can tell what it produces and what it does not 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 Guidelines5/5

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

Explicit routing is given: preferred for a quick initial design, use cold_plate for an unspecified GPU cold-plate concept, use get_template when customised parameters are needed, and continue with get_design_preview for pending results. Both the positive case and the alternatives are named with the condition that selects them.

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

All Gradient Dynamics: thermal and CFD simulation tools Inspect

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

Need Help?