Skip to main content
Glama

Configure optimization

configure_optimization
Idempotent

Configure an OpenMDAO driver and specify design variables, objective, and constraints to set up optimization, DOE, or analysis runs.

Instructions

Set the driver (scipy SLSQP/L-BFGS-B/trust-constr/COBYLA/Nelder-Mead, doe, analysis) and, when given, the design variables, objective and constraints. Gradient-based optimizers need ref/ref0 or scaler on every design variable.

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>",
      "driver": "<driver>"
    },
    "name": "configure_optimization"
  }
}

Input Schema

NameRequiredDescriptionDefault
driverYes
objectiveNo
problem_idYes
constraintsNo
design_varsNo

Output Schema

NameRequiredDescriptionDefault
nameNo
errorNo
inputsNo
statusNo
outputsNo
workdirNo
warningsNo
objectiveNo
problem_idNo
constraintsNo
design_varsNo
n_subsystemsNo
captured_outputNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.7/5.0
Behavior3/5

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

Annotations supply only idempotentHint=true, so the description carries most of the burden. It usefully discloses a validation constraint the agent would otherwise hit at runtime (gradient-based optimizers need ref/ref0 or scaler on every design variable), which is real value beyond the annotations. It does not say whether a repeated call replaces or merges existing driver/objective/constraint configuration, nor what happens on partial failure.

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 primary action and driver options, followed by the one hard constraint. The parenthetical optimizer list is dense but earns its place by mapping directly to the schema enum. 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.

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 no explanation, but this is a complex configuration tool with a required problem_id and a large nested spec set. The description leaves out the simple_ga driver, the overwrite-versus-merge behavior on repeated calls, and any prerequisite about the problem existing. Adequate for the main path, incomplete for edge cases.

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?

With schema description coverage reported at 0% for the top-level parameters, the description must carry the semantics, and it does explain the driver's accepted values and the role of design variables, objective and constraints. It also adds meaning the schema does not: the ref/ref0/scaler requirement is a cross-parameter rule that an agent could not infer from the type definitions alone. Remaining gaps (problem_id, units, bounds, maximize) are secondary to the core configuration story.

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?

Uses a specific verb ('Set') with the concrete resources it configures: driver, design variables, objective and constraints. It enumerates the scipy optimizer names plus the doe/analysis driver types, which separates it from configure_solvers and configure_approx_totals. However, the enumeration omits the simple_ga driver that the schema actually accepts, so the stated scope is slightly narrower than the real one.

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: 'when given' suggests the design variables, objective and constraints are optional, but nothing states when to pick scipy versus doe versus analysis, nor that a problem must already exist (problem_id is required but unexplained). The one real guideline is the gradient-based scaling requirement, which is a conditional rule rather than a routing rule.

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