Skip to main content
Glama

Bias controlled quant study pack — Atom

Bias-controlled quant study pack

bias_controlled_quant_study_pack
Read-onlyIdempotent

Submits a quant study-pack manifest (preregistered hypothesis, data hygiene, distribution and stationarity evidence, multiple-testing discipline, cost coverage, reproducibility) and returns a deterministic STUDY_PACK_COMPLETE / STUDY_PACK_NOT_COMPLETE / INSUFFICIENT_EVIDENCE verdict across seven sections, including computed cost-coverage, stability-across-periods and reported-vs-tested coherence checks, with per-check evidence. Audits the declared study pack; it does not run the study.

Tool call template

This tool declares no required parameters. Add optional parameters from the input schema as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {},
    "name": "bias_controlled_quant_study_pack"
  }
}

Input Schema

NameRequiredDescriptionDefault
dataNoData-hygiene evidence.
costsNoCost-coverage evidence, including the included list.
studyNoStudy the pack covers.
hypothesisNoHypothesis preregistration evidence.
distributionNoDistribution-reality evidence.
stationarityNoStationarity and stability evidence.
reproducibilityNoReproducibility evidence.
multiple_testingNoMultiple-testing discipline evidence.

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observed

TDQS

A3.9/5.0
Behavior3/5

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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive, closed-world), and the description is consistent with them: it is a pure validation returning a deterministic verdict. It adds real value by naming the exact verdict enum and the computed checks (cost-coverage, stability-across-periods, reported-vs-tested coherence) with per-check evidence. It does not say how missing or empty sections affect the verdict, which is the main behavioral unknown for an all-optional manifest.

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?

Front-loaded with the action and the return contract, and every clause earns its place by naming a verdict or a check. The single long sentence is dense and somewhat run-on, but there is no filler.

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

Completeness4/5

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

With no output schema, the description carries the return contract and does so well by naming the three verdicts and per-check evidence. For an 8-parameter nested-object manifest with zero required fields, it should also say which sections are necessary to reach a COMPLETE verdict and how absent sections are treated.

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 coverage is 100% and every parameter already carries a description, so the schema does the heavy lifting. The description enumerates the same seven evidence areas (hypothesis, hygiene, distribution/stationarity, multiple-testing, cost coverage, reproducibility) and highlights the 'included list' for costs, but adds little beyond the schema's own labels and defers field detail to SERVICE.md.

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

Purpose5/5

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

States a specific verb and resource ('Submits a quant study-pack manifest') and pins down the output ('returns a deterministic STUDY_PACK_COMPLETE / STUDY_PACK_NOT_COMPLETE / INSUFFICIENT_EVIDENCE verdict across seven sections'), plus an explicit non-goal ('it does not run the study'). An agent knows exactly what this does without opening the schema.

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

Usage Guidelines4/5

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

The closing sentence draws the critical boundary between auditing a declared pack and executing a study, which is the main misuse risk. There is no explicit when-to-use framing or prerequisite (e.g. that all seven evidence sections should be populated for a COMPLETE verdict), so it stops short of a 5.

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

Try in Browser

Glama MCP Gateway

Add one secure layer between your agents and this server.