Skip to main content
Glama
seanshin0214

Dr. QuantMaster MCP Server

by seanshin0214

psm_guide

Perform propensity score matching for causal inference by selecting matching methods and checking covariate balance in quantitative research.

Instructions

성향점수매칭 가이드 (추정, 매칭, 균형검정)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
matching_methodYes매칭 방법
balance_checkNo균형검정 포함

Implementation Reference

  • The main handler function for the 'psm_guide' tool. It returns a guide including steps for propensity score matching and balance metrics based on the input matching_method.
    function handlePsmGuide(args: Record<string, unknown>) {
      return {
        matching_method: args.matching_method,
        steps: [
          "1. Propensity score estimation (logit/probit)",
          "2. Check common support",
          "3. Perform matching",
          "4. Balance check (standardized differences <0.1)",
          "5. Estimate treatment effect on matched sample"
        ],
        balance_metrics: ["Standardized mean difference", "Variance ratio", "Overlap plots"]
      };
    }
  • The input schema definition for the 'psm_guide' tool, specifying parameters like matching_method (required, enum) and optional balance_check.
      name: "psm_guide",
      description: "성향점수매칭 가이드 (추정, 매칭, 균형검정)",
      inputSchema: {
        type: "object",
        properties: {
          matching_method: {
            type: "string",
            enum: ["nearest", "caliper", "kernel", "full"],
            description: "매칭 방법"
          },
          balance_check: { type: "boolean", description: "균형검정 포함" },
        },
        required: ["matching_method"],
      },
    },
  • The registration of the 'psm_guide' tool handler in the switch statement of handleToolCall function.
    case "psm_guide":
      return handlePsmGuide(args);
Behavior1/5

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

With no annotations provided, the description carries full burden for behavioral disclosure but provides none. It doesn't indicate whether this is a read-only informational guide, an interactive calculator, a code generator, or something else. It doesn't mention permissions needed, rate limits, side effects, or what kind of output to expect. The three Korean terms in parentheses are too vague to constitute meaningful behavioral information.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness3/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise (just 7 Korean characters plus 3 terms in parentheses), but this brevity comes at the cost of being under-specified rather than efficiently informative. While it's not verbose or repetitive, it fails to provide the essential information needed to understand the tool's function and use.

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

Completeness1/5

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

Given the complexity implied by the tool name (propensity score matching is a sophisticated statistical technique), the lack of annotations, and no output schema, the description is completely inadequate. It doesn't explain what the tool produces, how it should be used, what knowledge domain it addresses, or how it differs from related tools. For a statistical guidance tool with parameters, this minimal description leaves the agent guessing about fundamental aspects of the tool's operation.

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 100%, so the baseline is 3. The description doesn't add any meaningful parameter information beyond what's already in the schema - it mentions 'matching' and 'balance check' which correspond to the two parameters, but provides no additional context about parameter selection, dependencies, or practical implications. The description doesn't compensate for any gaps since there are none in the schema documentation.

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

Purpose2/5

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

The description '성향점수매칭 가이드 (추정, 매칭, 균형검정)' translates to 'Propensity Score Matching Guide (estimation, matching, balance check)' which is somewhat tautological - it restates the tool name 'psm_guide' and adds three Korean terms that are essentially synonyms or components of PSM. While it hints at the domain (propensity score matching), it doesn't specify what action the tool performs (e.g., 'generate', 'calculate', 'evaluate', 'implement') or what resource it operates on.

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

Usage Guidelines1/5

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

The description provides no guidance on when to use this tool versus the many sibling tools on the server. With 50+ sibling tools including various statistical guides (bayesian_guide, causal_design_guide, event_study_guide, etc.), there's no indication of when this PSM guide is appropriate versus alternatives like 'suggest_method' or 'compare_methods' or other causal inference tools.

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

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/seanshin0214/quantmaster-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server