Skip to main content
Glama

Run driver

run_driver

Executes the configured OpenMDAO driver from the current model point, records each run to a separate SQLite case file, and reports failures with success=false.

Instructions

Run the configured driver from the current point. Each run records to its own SqliteRecorder file (see query_cases). Failures are reported with success=false.

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>"
    },
    "name": "run_driver"
  }
}

Input Schema

NameRequiredDescriptionDefault
outputsNoPromoted names of outputs to return.
problem_idYes
case_prefixNo

Output Schema

NameRequiredDescriptionDefault
errorNo
driverNo
outputsNo
successNo
messagesNo
convergedNo
elapsed_sNo
objectiveNo
iterationsNo
constraintsNo
design_varsNo
exit_statusNo
failure_kindNo
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?

Annotations carry only a title, so the description must carry the behavioral load. It does disclose real side effects — each run writes its own SqliteRecorder file — and error semantics (success=false on failure), which are valuable. It stops short of saying whether runs are long-running or blocking, whether prior recorder files are overwritten, or what happens to solver/output state, so gaps remain for an execution tool with zero safety annotations.

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?

Three short sentences, front-loaded with the action, followed by the side effect and the failure convention. Nothing is redundant, though the parenthetical '(see query_cases)' is doing routing work that could be stated more directly.

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-shape explanation is not needed, and the description correctly flags the success=false convention. Still, for a 3-parameter execution tool with no behavioral annotations, the undocumented problem_id and case_prefix parameters leave an agent guessing at invocation details.

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 coverage is only 33%, with just 'outputs' documented in the schema. The description adds no meaning for any parameter — problem_id (the required one) and case_prefix (null-defaulted) are entirely unexplained in both places, and the interaction between case_prefix and the per-run recorder file is left opaque.

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?

States a specific verb and resource: run the configured driver from the current point. That is meaningfully distinct from siblings such as run_model, run_doe, and run_multistart, though the description never names an alternative to explicitly draw the boundary. An agent can infer the purpose, but must rely on names of siblings to confirm it.

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?

The phrase 'configured driver' and 'from the current point' imply this is used after configuration is in place, which is useful context. However, there is no explicit when-to-use versus when-not guidance, and no mention of prerequisites such as loading a problem or setting up solvers before calling it.

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