abaqus-mcp

Overview Schema Source Related Servers Discussions Admin

start_sweep

Run a parametric sweep of FEA designs with automatic correction and validation. Failed or implausible results are parked with diagnostics, and re-runs skip already completed designs.

Instructions

Run a parametric sweep, parking whatever needs judgement.

Each design goes through the autocorrect loop and then the validity gate. Anything that fails, or that converges to something not believable, is parked with full diagnostics rather than dropped. Resumable: re-running the same sweep name skips designs that already finished.

This blocks until the sweep completes, so keep the design count small from an interactive client. For a long unattended sweep, run the sweep module as a detached process instead.

Args: sweep_name: Name for this sweep; also its results directory. designs_json: JSON list of {"design_id":..., "inp":..., "params":{...}}. max_iters: Deterministic fix iterations allowed per design. cpus: CPUs per solver run. quasi_static: Whether to judge the event as quasi-static.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`cpus`	No
`max_iters`	No
`sweep_name`	Yes
`designs_json`	Yes
`quasi_static`	No

Output Schema

TableJSON Schema

Name	Required	Description	Default
`result`	Yes

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Sep 17, 2026

TDQS

A5/5.0

Behavior5/5

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

With no annotations to lean on, the description fully carries the behavioral burden. It discloses that the tool blocks, is resumable, runs each design through autocorrect and a validity gate, parks failed/unbelievable results rather than dropping them, and creates a results directory named after the sweep. This goes well beyond a basic summary.

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?

The description is front-loaded with the core purpose, followed by behavioral details, a practical blocking warning, and a compact parameter list. Every sentence adds useful information with no filler or repetition of the schema.

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 tool with five parametersative, no annotations, and an output schema available, this description is complete: it explains side effects, resumability, failure handling, blocking semantics, and parameter meanings. An agent can safely invoke and interpret this tool without seeking additional context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 0%, so the description must compensate, and it does. Every parameter is explained: sweep_name doubles as the results directory, designs_json has a concrete JSON shape, max_iters and cpus are scoped per design/solver run, and quasi_static is defined as controlling the judgment of the event.

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 opens with a specific verb and resource: 'Run a parametric sweep.' It then clarifies the distinguishing behavior — parking failures and unbelievable results with diagnostics instead of dropping them — which clearly separates it from sibling tools like run_simulation or sweep_status.

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?

The description gives explicit usage context: it blocks until completion and advises keeping design count small from an interactive client. It also names the alternative approach for long unattended sweeps — running the sweep module as a detached process — which is clear when-to-use and when-not-to-use guidance.

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