Skip to main content
Glama
priornerualnet-mcp

priornerualnet-mcp

by LatentVirtue

run_priorneuralnet_benchmark

Compare a prior-constrained neural network against parameter-matched MLPs on tabular data, then save validation scores, verdict, and run artifacts for review.

Instructions

Benchmark the prior-constrained network against parameter-matched MLPs.

Writes artifacts under <output_dir>/<run_id>/ (manifest.json, report.html, concept_activations.parquet, final_model.pt, concept_drivers.json) and returns the run id, verdict, per-model val scores and a pointer to the full manifest.

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": {
      "data_path": "<data_path>",
      "prior_path": "<prior_path>",
      "target_column": "<target_column>"
    },
    "name": "run_priorneuralnet_benchmark"
  }
}

Input Schema

NameRequiredDescriptionDefault
epochsNo
n_splitsNo
data_pathYes
output_dirNoruns
prior_pathYes
target_columnYes
run_learning_curveNo

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

With no annotations present, the description carries the full burden and does add real behavioral value: it discloses that the call writes artifacts to `<output_dir>/<run_id>/`, enumerates the exact file set, and describes the return payload (run id, verdict, per-model val scores, manifest pointer). It omits important traits such as runtime/expense (defaults imply 60 epochs × 5 splits), whether an existing run_id directory is overwritten, and whether GPU or specific permissions are required.

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 front-loaded sentences: the action comes first, then the side effects and return values. The artifact enumeration is long but earns its place by telling the agent exactly what will be written; little is wasted.

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?

For a fairly complex, long-running benchmark with no output schema and no annotations, the description covers outputs and artifacts well but leaves parameter meanings and cost/overwrite behavior unexplained. An agent could call it, but would be guessing about the inputs and the expense.

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

Parameters3/5

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 only partially does: it clarifies output_dir behavior (artifacts land under `<output_dir>/<run_id>/`) and reveals that run_id is generated rather than supplied. The five other parameters — data_path, prior_path, target_column, epochs, n_splits, run_learning_curve — receive no explanation of expected formats or semantics, leaving a substantial gap the schema does not fill.

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 comparison ('Benchmark the prior-constrained network against parameter-matched MLPs'), so the agent knows exactly what the call does. It does not name or differentiate itself from siblings like validate_domain_prior or inspect_concept_drivers, so an agent must infer that this is the execution step rather than a validation or inspection step.

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 by the purpose: the tool presumably runs after a prior has been built and validated via validate_domain_prior, but the description never says so and gives no prerequisites, cost warnings, or when-not-to-use conditions. An agent can guess the ordering but gets no explicit routing guidance.

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