Skip to main content
Glama

Run DOE

run_doe

Runs DOE over OpenMDAO design variables via DOEDriver using Latin hypercube, full factorial, uniform, or explicit cases; failed points are reported without failing the run.

Instructions

Design of experiments over the design variables: Latin hypercube (scipy.stats.qmc), full factorial, uniform, or an explicit list, run through DOEDriver. Failed points are reported, not fatal.

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": {
      "problem_id": "<problem_id>",
      "generator": "<generator>"
    },
    "name": "run_doe"
  }
}

Input Schema

NameRequiredDescriptionDefault
generatorYes
responsesNoPromoted names of outputs to return.
problem_idYes
feasibility_tolNo
max_cases_returnedNo

Output Schema

NameRequiredDescriptionDefault
casesNo
errorNo
n_casesNo
n_failedNo
truncatedNo
recorder_pathNo
captured_outputNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.2/5.0
Behavior3/5

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

With only a title annotation, the description still contributes one genuinely useful behavioral fact: 'Failed points are reported, not fatal', which tells the agent that a partially failing DOE returns results rather than raising. However, it does not disclose that the run executes the model/driver (potentially expensive), whether it mutates problem state or records cases, or how results relate to sibling retrieval tools like query_cases.

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?

Two sentences, front-loaded with the core verb and resource, with the sampling options and the failure semantics appended. It is dense but every clause carries information; only the scipy/stats.qmc parenthetical is closer to implementation trivia than agent-facing guidance.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

An output schema exists, so return values need not be explained, and the failure-mode note covers the main reliability question. Still missing for a moderately complex, multi-parameter execution tool: cost/blocking behavior, side effects on the problem, and guidance on max_cases_returned versus the size of the generated design.

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

Parameters2/5

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

Schema description coverage is only 20%, so the description carries most of the burden. It does map the four generator types to their enum values and clarify that sampling happens internally before being handed to OpenMDAO's ListGenerator, but it says nothing about feasibility_tol, max_cases_returned, or responses, leaving three of five parameters undocumented in either place.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description names a specific operation (design of experiments over the design variables) and enumerates the supported sampling strategies (Latin hypercube via scipy.stats.qmc, full factorial, uniform, explicit list) plus the execution path (DOEDriver). That is enough to tell it apart from siblings like run_model or compute_totals, though it never explicitly contrasts itself with run_driver or run_multistart.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

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

Usage is only implied: the agent can infer 'use this when you want to sweep design variables across a space.' There is no statement of when to prefer run_driver, run_multistart, or an input sweep instead, and no prerequisites (e.g., that a problem must be loaded/configured first) are given.

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