Skip to main content
Glama
priornerualnet-mcp

priornerualnet-mcp

by LatentVirtue

inspect_concept_drivers

Retrieves a concept's attribution rank and top-k feature drivers to explain model behavior and validate priors in p >> n tabular runs.

Instructions

Return a concept's attribution rank plus its top-k feature drivers.

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": {
      "run_id": "<run_id>",
      "concept_name": "<concept_name>"
    },
    "name": "inspect_concept_drivers"
  }
}

Input Schema

NameRequiredDescriptionDefault
top_kNo
run_idYes
output_dirNoruns
concept_nameYes

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

C2.7/5.0
Behavior2/5

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

With no annotations, the description carries the full disclosure burden. "Return" weakly implies a read-only operation, but nothing is said about whether a prior run must exist, whether the call is expensive, whether it writes anything to output_dir, or what the result contains beyond two named fields.

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?

A single front-loaded sentence with no filler, and the key outputs are stated first. It is arguably too terse for a four-parameter tool with no schema descriptions, but there is no wasted wording to trim.

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

Completeness2/5

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

No output schema, no annotations, and zero parameter description coverage mean the description is the only documentation channel, and it covers only half the parameters. An agent could not confidently supply run_id or output_dir or anticipate the response shape from this definition.

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 0% across four parameters, so the description must compensate and largely does not. It implies top_k controls the driver count and concept_name selects the concept, but run_id and output_dir are never explained, including the surprising fact that an inspection tool takes an output directory.

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 ("Return") and names concrete outputs: a concept's attribution rank and its top-k feature drivers. An agent can tell this is an inspection/readout tool, distinct from the benchmark and validation siblings, though the description never explicitly contrasts with them.

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

Usage Guidelines2/5

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

No guidance on when to call this versus the sibling benchmark or validation tools, and no stated prerequisites such as requiring an existing run or trained model. The agent must infer the workflow position from the tool name alone.

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