Skip to main content
Glama
seanshin0214

Dr. QuantMaster MCP Server

by seanshin0214

causal_design_guide

Guide users through causal inference design selection and implementation for methods like DID, RDD, IV, PSM, and synthetic control, covering identification, assumptions, and practical application.

Instructions

인과추론 설계 가이드 (DID, RDD, IV, PSM, Synth)

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
designYes인과추론 설계
aspectNo가이드 측면

Implementation Reference

  • The handler function that implements the logic for the causal_design_guide tool. It takes input 'design' and returns a predefined guide containing identification strategy, key tests, threats, and code snippets for specified causal designs (did, rdd, iv).
    function handleCausalDesignGuide(args: Record<string, unknown>) {
      const design = args.design as string;
      const guides: Record<string, any> = {
        did: {
          identification: "Parallel Trends Assumption",
          key_tests: ["Pre-trend test", "Placebo test", "Event study"],
          threats: ["Anticipation", "Spillover", "Composition change"],
          stata: "did_imputation, csdid, reghdfe",
          r: "did, fixest::feols"
        },
        rdd: {
          identification: "Local randomization at cutoff",
          key_tests: ["McCrary density test", "Covariate balance at cutoff"],
          threats: ["Manipulation", "Compound treatment"],
          stata: "rdrobust",
          r: "rdrobust, rdd"
        },
        iv: {
          identification: "Exclusion restriction + Relevance",
          key_tests: ["First-stage F (>10)", "Overidentification (Sargan/Hansen)"],
          threats: ["Weak instruments", "Invalid exclusion"],
          stata: "ivreg2, ivregress",
          r: "ivreg, fixest::feols"
        }
      };
    
      return { design, guide: guides[design] || { message: "Design guide not found" } };
    }
  • Registers the causal_design_guide tool in the tools array, including its name, description, and inputSchema with required 'design' parameter (enum of causal methods) and optional 'aspect'.
      name: "causal_design_guide",
      description: "인과추론 설계 가이드 (DID, RDD, IV, PSM, Synth)",
      inputSchema: {
        type: "object",
        properties: {
          design: {
            type: "string",
            enum: ["did", "rdd", "iv", "psm", "synthetic_control", "event_study"],
            description: "인과추론 설계"
          },
          aspect: {
            type: "string",
            enum: ["identification", "assumptions", "implementation", "threats", "all"],
            description: "가이드 측면"
          },
        },
        required: ["design"],
      },
    },
  • Defines the input schema for the causal_design_guide tool, specifying an object with 'design' (required, enum of causal designs) and optional 'aspect' (enum of guide aspects).
    inputSchema: {
      type: "object",
      properties: {
        design: {
          type: "string",
          enum: ["did", "rdd", "iv", "psm", "synthetic_control", "event_study"],
          description: "인과추론 설계"
        },
        aspect: {
          type: "string",
          enum: ["identification", "assumptions", "implementation", "threats", "all"],
          description: "가이드 측면"
        },
      },
      required: ["design"],
    },
Behavior2/5

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It only lists design types and aspects without explaining what the tool does behaviorally—e.g., whether it generates text, provides summaries, or returns structured data. There's no mention of output format, potential errors, or any operational traits, leaving significant gaps in understanding how the tool functions.

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?

The description is very concise, consisting of a single phrase that lists key terms. It's front-loaded with the main topic but lacks structure or elaboration. While efficient, it may be overly terse for a tool with multiple parameters and no output schema, potentially under-specifying its purpose. However, it avoids redundancy and waste.

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?

Given the complexity of causal inference methods and the lack of annotations and output schema, the description is incomplete. It doesn't explain what the tool returns, how to interpret results, or any behavioral context. With sibling tools covering similar topics, more detail is needed to distinguish this tool's role and ensure users can apply it correctly without confusion.

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?

The schema description coverage is 100%, with clear enum values for 'design' and 'aspect' parameters documented in the schema. The description adds no additional semantic meaning beyond what's in the schema, such as explaining the relationships between designs and aspects or providing usage examples. Since the schema is comprehensive, a baseline score of 3 is appropriate, as the description doesn't compensate but also doesn't detract.

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

Purpose3/5

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

The description '인과추론 설계 가이드 (DID, RDD, IV, PSM, Synth)' states it provides guidance for causal inference designs, listing specific methods. However, it's vague about what the guidance entails (e.g., explanations, examples, or templates) and doesn't clearly distinguish it from sibling tools like 'get_method_guide' or 'suggest_method', which might overlap in purpose. The description is in Korean, which adds specificity but doesn't fully clarify the tool's function beyond a general topic.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention any prerequisites, context for selection among the listed designs, or comparisons to sibling tools such as 'event_study_guide' or 'psm_guide', which might cover similar ground. Without explicit usage instructions, users must infer based on the parameter names alone.

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