Skip to main content
Glama
mikenguyen13

Research Methods Library

by mikenguyen13
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

Search the research methods library

search
Read-onlyIdempotent

Find relevant sections in research methods textbooks and an R package for statistics, causal inference, econometrics, and machine learning, with code and citations.

Instructions

Search sections of textbooks and an R package on research methods and data analysis: statistics and hypothesis testing, regression and generalized linear models, causal inference (difference-in-differences, synthetic control, regression discontinuity, instrumental variables, matching, double machine learning), econometrics, experimental design, survey methods, marketing research, credit scoring, machine learning, and AI. Returns matching sections with their ids, a link, a snippet, the code languages they contain, and a citation.

Input Schema

NameRequiredDescriptionDefault
limitNoNumber of results (default 8).
queryYesWhat to look for, in plain words, e.g. "staggered difference-in-differences with never-treated controls".
sourceNoLimit to one work: data_analysis (A Guide on Data Analysis); causalverse (causalverse: The All-in-One Causal Inference Toolkit); credit_score (Credit Scoring: Theory, Methods, and Practice); marketing_research (Marketing Research: A Technical and Academic Treatment); ai_in_action (AI in Action: A Reference for Artificial Intelligence); advanced_data_analysis (Advanced Data Analysis); tidy_finance_vn (Applying Tidy Finance with Python to Vietnam); tidy_finance_vn_vi (Tài Chính Ứng Dụng với Python); mlpy (Machine Learning in Python); publications (Research Articles and Publications).
languageNoPrefer sections with code in this language.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed2 schema fields changedv0.1.1
    • changedInput schema / properties / source / description
      Previous value: -"Limit to one work: data_analysis (A Guide on Data Analysis); causalverse (causalverse: The All-in-One Causal Inference Toolkit); credit_score (Credit Scoring: Theory, Methods, and Practice); marketing_research (Marketing Research: A Technical and Academic Treatment); ai_in_action (AI in Action: A Reference for Artificial Intelligence)."New value: +"Limit to one work: data_analysis (A Guide on Data Analysis); causalverse (causalverse: The All-in-One Causal Inference Toolkit); credit_score (Credit Scoring: Theory, Methods, and Practice); marketing_research (Marketing Research: A Technical and Academic Treatment); ai_in_action (AI in Action: A Reference for Artificial Intelligence); advanced_data_analysis (Advanced Data Analysis); tidy_finance_vn (Applying Tidy Finance with Python to Vietnam); tidy_finance_vn_vi (Tài Chính Ứng Dụng với Python); mlpy (Machine Learning in Python); publications (Research Articles and Publications)."
    • changedInput schema / properties / source / enum
      Previous value: -[
-  "data_analysis",
-  "causalverse",
-  "credit_score",
-  "marketing_research",
-  "ai_in_action"
-]New value: +[
+  "data_analysis",
+  "causalverse",
+  "credit_score",
+  "marketing_research",
+  "ai_in_action",
+  "advanced_data_analysis",
+  "tidy_finance_vn",
+  "tidy_finance_vn_vi",
+  "mlpy",
+  "publications"
+]
  2. First observedv0.1.0

TDQS

A3.8/5.0
Behavior4/5

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

Annotations already declare readOnly=true, idempotent=true, destructive=false and closed-world, so the safety profile is covered. The description adds genuinely new context by disclosing the return shape (ids, link, snippet, contained code languages, citation) which, with no output schema present, is the only place an agent learns what comes back.

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?

Structure is front-loaded: purpose first, return contract second. The long parenthetical topic list is verbose but earns its place as discovery vocabulary for a broad corpus. Two sentences, no filler, only mild bloat in the enumeration.

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

Completeness5/5

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

For a read-only search tool with full schema coverage and no output schema, the description supplies both the corpus scope and the return contract, which is everything an agent needs to invoke it correctly. No annotated safety behavior or parameter is left unexplained.

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% and the enumerated source/language values are fully documented in the schema, so the description does not need to compensate. It adds nothing about how limit interacts with ranking or how language acts as a preference rather than a hard filter, so baseline 3 applies.

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?

The description states a specific verb (search) and resource (sections of textbooks and an R package on research methods/data analysis), and enumerates the topical corpus, so an agent knows exactly what is being searched. It does not, however, distinguish itself from siblings like get_code or cite, which also surface library content.

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 implied by the topic inventory and the query parameter example ('staggered difference-in-differences with never-treated controls'), which signals the intended retrieval use case. There is no explicit when-to-use versus when-not guidance, and no sibling (get_code, cite, choose_method) is named as the alternative for adjacent needs.

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

Deploy Server

Other Tools