Gradient Dynamics: thermal and CFD simulation

Estimate cost and time

estimate_cost

Read-onlyIdempotent

How much will this cost and how long will it take? Free and needs no account. Estimate how many credits a thermal, CFD or meshing run will use and how long it will take, before running it. Use before create_mesh or run_simulation, and to compare options; give the planned cell count (or an owned mesh_artifact_id) and solver steps. Signed in, it also says whether your plan, credits and key budget would admit the run. For explicitly authorized automatic mesh retries, set mesh_max_attempts to the same total attempt budget as the mesh request so the upper time estimate covers it. Read-only: no inputs are uploaded and no compute starts. Meshes are charged by delivered cells (failed meshes and automatic rebuilds are free), predictions per success, simulations by measured compute; the high value is held.

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": {
      "operation": "<operation>"
    },
    "name": "estimate_cost"
  }
}

Input Schema

Name	Required	Description	Default
`gpu`	No	Simulation GPU type: B200 (default) or H100.
`cells`	No	Mesh target cells (operation=mesh) or the simulation mesh's cell count. Defaults to 1 million for meshes; for simulations supply cells or mesh_artifact_id.
`gpu_count`	No	Simulation GPUs (default 1).
`operation`	Yes
`architecture`	No	Fluxcore GPU solver. Use 'fluxcore'; 'workhorse' remains an accepted compatibility identifier for saved requests and deployed workers.	fluxcore
`max_iterations`	No	Steady RANS/CHT iteration ceiling (default 6000).
`simulation_type`	No		rans
`inner_iterations`	No
`mesh_artifact_id`	No	Owned mesh whose verified cell count to use (signed-in callers only).
`n_physical_steps`	No
`mesh_max_attempts`	No	Total authorized full mesh attempts, for the upper time estimate. Use 1 for retry_policy=review; for automatic, copy max_remesh_iterations (octree/OpenFOAM) or max_target_iterations (structured). Read-only estimation does not authorize a retry. Automatic rebuilds are not charged: a mesh costs the same credits however many attempts it takes.

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedNov 13, 2026

TDQS

A4.7/5.0

Behavior5/5

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

Annotations already declare readOnly/idempotent/non-destructive, but the description adds substantial context beyond them: no inputs uploaded, no compute starts, free and no account needed, and what happens when signed in (plan/credit/key budget admission check). It also discloses the billing model — meshes charged by delivered cells with failed/rebuilt meshes free, predictions per success, simulations by measured compute, with a high hold — which materially affects how an agent interprets the estimate.

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 question and the primary use case, then layered detail. Dense but mostly earned; the billing paragraph is long and packs several clauses into one sentence, which slightly hurts scanability.

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?

Covers purpose, prerequisites, billing semantics, and the retry-budget nuance for a complex 11-param tool, and an output schema exists so return values need no explanation. Minor gaps remain around how the estimate varies by operation type (geometry/prediction) and the non-obvious GPU/architecture parameters.

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?

With 64% schema coverage across 11 params, the description compensates for the important ones: it clarifies cells as a planned cell count versus a mesh_artifact_id lookup, requires solver steps, and explains that mesh_max_attempts must match the mesh request's total attempt budget so the upper time bound is correct. It leaves operation enum values and GPU/architecture parameters to the schema, so it doesn't fully close the coverage gap.

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 concrete verb and resource: estimating credits and wall-clock time for a thermal, CFD, or meshing run before executing it. It explicitly separates itself from create_mesh and run_simulation, so an agent can pick it without opening a 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?

Gives explicit when-to-use guidance ('Use before create_mesh or run_simulation, and to compare options') and states the required inputs (planned cell count or an owned mesh_artifact_id, plus solver steps). The conditional signed-in vs anonymous behavior and the mesh_max_attempts matching rule are also spelled out.

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?