| startsession | A comprehensive tool for initializing a new quantitative research session, providing structured information about ongoing research projects, datasets, statistical models, and recent research activities. When to use this tool: Beginning a new quantitative analysis session Getting oriented to your current research state across multiple projects Planning which research elements to focus on in the current session Reviewing recent research activities and progress Identifying active research projects and their status Exploring available datasets for analysis Reviewing current research questions Examining statistical models and their performance Viewing recent visualizations of your data Establishing research context before diving into specific analysis tasks Re-engaging with your research after time away Prioritizing high-priority research tasks Tracking the status of various research activities Understanding sequential research processes
Key features: Generates a unique session identifier for tracking research activities Retrieves and displays recent research sessions with summaries Lists active research projects with status information Provides a sample of available datasets with key information Presents current research questions guiding your studies Highlights recent statistical models with performance metrics Displays recent visualizations with brief descriptions Formats information in an easily scannable format for quick orientation Integrates with the loadcontext tool for deeper exploration Maintains continuity between research sessions Tracks research session history for progress review Displays high-priority research tasks needing attention Shows status information for key research activities Presents sequential relationships between research processes
Parameters explained:
No parameters required - the tool automatically retrieves all relevant context. Return information: Recent research sessions (up to 3) with: Date Project name Brief summary
Active research projects with: Available datasets (up to 5) with: Research questions (up to 5) with: Recent statistical models with: Recent visualizations with: Visualization name Type (chart, plot, etc.) Associated dataset
High-priority research tasks (up to 5) with: Upcoming research activities (up to 3) with:
Status and Priority Information: Research activities are displayed with their current status values High-priority tasks are prominently highlighted for attention Valid status values include: active, completed, pending, abandoned Priority values (high, low) help indicate which tasks need immediate attention Status is retrieved through has_status relations Priority is retrieved through has_priority relations
Sequential Process Information: Upcoming activities show prerequisite tasks that must be completed first Research phases are presented in their logical sequence The precedes relation is used to determine activity ordering Sequential relationships help visualize the research workflow
Session Workflow: Start a research session with startsession Review the provided context to decide what to focus on Use loadcontext to retrieve detailed information about specific research elements Conduct your analysis, adding new elements with buildcontext as needed End the session with endsession to record your research progress
You should: Begin each focused research period with startsession to establish context Review recent sessions to maintain continuity in your research Identify active projects that require attention Note available datasets for potential analysis Consider current research questions that need investigation Review existing statistical models before creating new ones Examine recent visualizations to understand data representation Prioritize high-priority tasks for immediate attention Check the status of research activities to maintain progress awareness Consider sequential relationships when planning your research activities Use the session ID when using other tools to maintain session tracking After completing a session, record your progress using endsession Establish a regular cadence of research sessions to maintain momentum Use the structured overview to make deliberate choices about where to focus your analytical effort
|
| buildcontext | A versatile tool for constructing and enhancing the quantitative research knowledge graph by adding new research elements, relationships, and observations. When to use this tool: Creating new research entities (projects, datasets, variables, hypotheses, statistical tests, etc.) Establishing relationships between research elements (e.g., connecting variables to datasets, statistical tests to hypotheses) Adding observations, properties, or metadata to existing research entities Building the research corpus incrementally as data collection and analysis progress Organizing and structuring quantitative data within your research framework Documenting statistical analyses, models, and their results Tracking research questions and linking them to findings Creating visualizations and connecting them to data and analyses Setting status values for research activities and entities Assigning priorities to research tasks and activities Defining sequential relationships between research processes
Key features: Creates three distinct types of knowledge graph elements: entities, relations, and observations Supports specialized quantitative research entity types (projects, datasets, variables, hypotheses, statistical tests, etc.) Validates entity and relation types against predefined standards for the quantitative research domain Handles batch creation of multiple entities or relations in a single operation Returns confirmation with details of created elements Ensures proper data typing and structure for the quantitative research knowledge graph Enables comprehensive documentation of statistical analysis processes Supports status and priority assignment through entity-relation model Enables sequential relationships through precedes relation
Parameters explained: type: The type of creation operation to perform
Accepts: "entities", "relations", or "observations" Determines how the data parameter is interpreted
data: The content to add to the knowledge graph (structure varies by type):
For "entities": An array of objects, each containing: name: Unique identifier for the entity entityType: One of the valid entity types (project, dataset, variable, hypothesis, statisticalTest, result, analysisScript, visualization, model, literature, researchQuestion, finding, participant, status, priority) observations: Array of strings containing notes or properties about the entity
For "relations": An array of objects, each containing: from: Name of the source entity to: Name of the target entity relationType: The type of relationship between entities (e.g., correlates_with, predicts, tests, analyzes, produces, has_status, has_priority, precedes)
For "observations": Either a single object or an array of objects, each containing:
Valid entity types: project: Overall research study dataset: Collection of data used for analysis variable: Specific measurable attribute in a dataset hypothesis: Formal testable statement statisticalTest: Analysis method applied to data result: Outcome of statistical analysis analysisScript: Code used to perform analysis visualization: Visual representation of data model: Statistical/mathematical model literature: Academic sources researchQuestion: Formal questions guiding the study finding: Results or conclusions participant: Research subjects status: Entity status values priority: Entity priority values
Valid relation types: correlates_with: Statistical correlation between variables predicts: Predictive relationship from independent to dependent variable tests: Statistical test examines hypothesis analyzes: Analysis performed on dataset produces: Analysis produces result visualizes: Visualization displays data or result contains: Hierarchical relationship part_of: Entity is part of another entity depends_on: Dependency relationship supports: Evidence supporting a hypothesis or finding contradicts: Evidence contradicting a hypothesis or finding derived_from: Entity is derived from another entity controls_for: Variable/method controls for confounds moderates: Variable moderates a relationship mediates: Variable mediates a relationship implements: Script implements statistical test/model compares: Statistical comparison between groups/variables includes: Model includes variables validates: Validates a model or result cites: References literature has_status: Links entity to its status has_priority: Links entity to its priority precedes: Entity comes before another entity in sequence
Status information: Valid status values include: active, completed, pending, abandoned Status is assigned through the has_status relation type Status helps track progress of research activities
Priority information: Valid priority values: high, low Priority is assigned through the has_priority relation type Priority helps identify critical research tasks
Sequential Process Information: The precedes relation establishes logical ordering between research processes Sequential relationships document the flow of the research methodology Helps maintain proper order in multi-step analysis procedures
Return information: Error handling: Validates entity types against the predefined list for quantitative research Validates relation types against acceptable standards Returns descriptive error messages for invalid inputs Gracefully handles type mismatches and formatting errors
You should: Use consistent naming conventions for entities to facilitate relationships and retrieval Begin by creating projects and datasets before more specific research elements Add detailed observations to entities to enhance context and retrievability Create relationships to build a comprehensive network of interconnected research data Document statistical methodology thoroughly by connecting tests, variables, and hypotheses Add statistical results with appropriate metadata (p-values, effect sizes, confidence intervals) Create visualizations and link them to the data they represent Use relations to document the flow of analysis from data to findings Connect literature to support hypotheses and contextualize findings Structure models with clear relationships to the variables they include Document analysis scripts with information about their purpose and implementation Use has_status relations to track the progress of research activities (active, completed, pending, abandoned) Use has_priority relations to indicate important research elements (high, low) Use precedes relations to establish sequences in research methodologies
|
| deletecontext | A precise tool for removing elements from the quantitative research knowledge graph, enabling researchers to maintain data accuracy and refine their analytical framework. When to use this tool: Removing incorrect or duplicate research entities Deleting erroneous relationships between research elements Clearing outdated observations from research entities Restructuring your research framework as analysis evolves Removing invalid statistical tests or models Correcting relationships between variables, datasets, or results Cleaning up the knowledge graph during research refinement phases Eliminating deprecated hypotheses or findings that are no longer supported Removing preliminary analyses that have been superseded by more rigorous methods Reorganizing your analytical structure by removing and recreating elements Updating status assignments when research activities change state Modifying priority assignments as research focus shifts Restructuring sequential relationships between research processes
Key features: Provides targeted deletion capabilities for three distinct types of knowledge graph elements: entities, relations, and observations Maintains knowledge graph integrity during deletion operations Supports batch deletion of multiple items in a single operation Returns clear confirmation of deletion results Preserves the overall structure of the research knowledge graph while removing specific elements Performs validation to ensure deletion requests are properly formatted Handles status and priority relation management Supports modification of sequential process relationships
Parameters explained: type: The type of deletion operation to perform
Accepts: "entities", "relations", or "observations" Determines how the data parameter is interpreted
data: The elements to remove from the knowledge graph (structure varies by type):
For "entities": Array of entity names to delete For "relations": Array of relation objects, each containing: from: Name of the source entity to: Name of the target entity relationType: Type of relationship to remove (e.g., "correlates_with", "has_status", "has_priority", "precedes") Example: [{ "from": "Variable_Age", "to": "Variable_Income", "relationType": "correlates_with" }]
For "observations": Array of objects, each containing: entityName: Name of the entity to remove observations from observations: Array of specific observations to remove Example: [{ "entityName": "Dataset_Main", "observations": ["size:1000", "collection_date:2022-05-15"] }]
Deletion behavior by type: Entities: Removes the specified entities and all their associated relations from the knowledge graph Relations: Removes only the specified relationships, leaving the connected entities intact Observations: Removes specific observations from entities while preserving the entities themselves
Status and Priority Management: When deleting status or priority entities, be aware of the impact on entities that reference them For changing an entity's status, delete the existing has_status relation before creating a new one For changing priority, delete the existing has_priority relation before creating a new one Status values (active, completed, pending, abandoned) are managed through relations, not direct properties Priority values (high, low) are managed through relations, not direct properties
Sequential Process Management: Removing precedes relations affects the logical flow of research processes When reorganizing research phases, update all affected precedes relations Consider restructuring sequential relationships after deletion to maintain methodological continuity Sequential relationships are important for maintaining proper order in multi-step analyses
Safety considerations: Entity deletion is permanent and will also remove all relationships involving those entities Consider exporting or backing up your research knowledge graph before performing large-scale deletions For sensitive operations, consider removing specific observations rather than entire entities When removing statistical tests or results, consider the impact on your overall analysis framework Status changes should be carefully managed to maintain accurate research progress tracking Changes to sequential relationships may affect dependent research activities
Return information: You should: Be specific in your deletion requests to avoid unintended data loss Use relations deletion when you want to disconnect entities without removing them For observations, provide the exact observations to ensure only the intended content is removed When restructuring your analysis, consider how deletions will affect related elements Use deletecontext in conjunction with buildcontext to refine and evolve your research framework Regularly review your knowledge graph for elements that may need to be removed or updated Consider the cascading effects of entity deletion on your overall research structure Delete outdated statistical results when new analyses are performed Remove incorrect relationships between variables when better understanding is gained When updating entity status, delete the old has_status relation before creating a new one When updating entity priority, delete the old has_priority relation before creating a new one Maintain logical consistency when modifying sequential analysis relationships
|
| advancedcontext | A sophisticated query tool for exploring, analyzing, and retrieving complex information from the quantitative research knowledge graph. When to use this tool: Retrieving a comprehensive view of your entire research knowledge structure Searching for specific research entities across your quantitative data projects Getting detailed information about particular research projects, datasets, or statistical elements Exploring relationships between variables and their statistical properties Analyzing hypothesis test results and their implications Retrieving statistical model performance metrics Accessing visualization galleries for specific projects or datasets Examining variable distributions and their statistical properties Finding connections between different aspects of your research Creating statistical reports or summaries from your data Exploring the relationships between research questions and findings Identifying entities by status to track research progress Filtering tasks by priority to manage research workflow Analyzing sequential relationships between research processes
Key features: Offers specialized operations for querying different aspects of quantitative research data Retrieves complete or filtered views of the research knowledge graph Provides flexible search capabilities across all research entities Supports detailed exploration of specific entities by name Generates specialized views for projects, datasets, hypotheses, and variables Retrieves statistical results, visualizations, and model performance metrics Provides detailed variable distribution analysis Identifies related entities to explore connections within your research Returns consistently structured JSON responses for easy processing Facilitates depth and breadth exploration of quantitative data Supports status-based filtering of research entities Enables priority-based task management Provides sequential process analysis capabilities
Parameters explained: type: The type of query operation to perform
Accepts one of the specialized operations: "graph", "search", "nodes", "project", "dataset", "hypothesis", "variables", "statistics", "visualizations", "model", "question", "distribution", "related", "status", "priority", "sequence" Determines how the params parameter is interpreted
params: Operation-specific parameters (structure varies by type):
For "graph": No parameters needed (retrieves the full research knowledge graph) For "search": Object containing: For "nodes": Object containing: For "project": Object containing: For "dataset": Object containing: For "hypothesis": Object containing: For "variables": Object containing: For "statistics": Object containing: For "visualizations": Object containing: For "model": Object containing: For "question": Object containing: For "distribution": Object containing: For "related": Object containing: For "status": Object containing: statusValue: The status value to filter by (e.g., "active", "completed", "pending", "abandoned")
For "priority": Object containing: For "sequence": Object containing:
Operation details: graph: Returns the complete research knowledge graph with all entities and relationships search: Performs text-based search across entity names and observations nodes: Retrieves detailed information about specific entities by name project: Returns comprehensive project information including datasets, hypotheses, tests, and findings dataset: Provides detailed dataset analysis with variables, descriptive statistics, and correlations hypothesis: Retrieves hypothesis tests and their results for a project or specific hypothesis variables: Examines relationships between a variable and other variables (correlations, dependencies) statistics: Collects statistical test results for a project, optionally filtered by test type visualizations: Returns visualization metadata and descriptions for a project or dataset model: Provides detailed model performance metrics, parameters, and validation results question: Retrieves research question details, related hypotheses, and supporting findings distribution: Analyzes the statistical distribution of a variable with descriptive stats and normality tests related: Identifies all entities directly connected to a specific entity status: Retrieves all entities with a specific status value priority: Retrieves all entities with a specific priority value sequence: Identifies sequential relationships for a specific entity showing preceding and following entities
Status and Priority Information: Status queries return entities organized by their current research stage Priority queries help identify critical research tasks and elements Status values include: active, completed, pending, abandoned Priority values include: high, low Status and priority are assigned through has_status and has_priority relations
Sequential Process Information: Sequence queries identify entities that come before or after in a research process Sequential relationships help visualize the research workflow and methodology The sequence operation shows both incoming and outgoing precedes relations Process sequences are essential for understanding multi-step analytical procedures
Return information: You should: Start with broad queries ("graph", "search") to explore your research corpus Use specific entity queries ("nodes", "project", "dataset") for detailed information Examine variable relationships and distributions to understand your data Review hypothesis tests and statistical results to evaluate evidence Explore model performance metrics to assess predictive accuracy Use visualization galleries to communicate research findings Examine research questions and their supporting evidence Use status queries to identify all entities at a particular research stage Use priority queries to focus on high-priority research tasks Use sequence queries to understand process flows in your research methodology Combine multiple operations to build a comprehensive understanding of your research Use the related operation to discover connections between entities Apply search filters to find specific types of research elements
|
| loadcontext | A powerful tool for retrieving detailed contextual information about quantitative research entities, providing rich statistical insights tailored to each entity type. When to use this tool: Retrieving comprehensive information about research projects, datasets, variables, and statistical elements Exploring the statistical relationships between variables Examining hypothesis tests and their results Reviewing model performance metrics and parameters Analyzing dataset properties and descriptive statistics Inspecting visualizations related to specific datasets or projects Understanding statistical test results and their significance Preparing for statistical analysis by establishing data context Examining variable distributions and correlations Getting a holistic view of quantitative research progress Tracking research activities by their current status Managing tasks based on their assigned priorities Understanding sequential relationships between research processes
Key features: Provides richly formatted, context-aware information about quantitative research entities Adapts output format based on entity type (project, dataset, variable, model, hypothesis, statistical_test) Presents both direct entity information and related statistical elements Shows statistical metrics, p-values, and significance levels Tracks entity views within the current research session Formats information in a structured, readable markdown format Highlights relationships between variables and statistical tests Presents performance metrics for statistical models Shows dataset characteristics and variable properties Includes status information for tracking research progress Displays priority assignments for critical research elements Visualizes sequential relationships between research processes
Parameters explained: entityName: Required - The name of the entity to retrieve context for
entityType: Optional - The type of entity being retrieved
Default: "project" Helps the system format the output appropriately Common types include: "project", "dataset", "variable", "model", "hypothesis", "statistical_test", "status", "priority"
sessionId: Optional - The current session identifier
Each entity type returns specialized context information: Project: Shows project status (via has_status), description, datasets, hypotheses, statistical tests, models, key visualizations, and priority (via has_priority) Dataset: Displays project affiliation, status (via has_status), size, variable count, descriptive statistics, visualizations, and models trained on it Variable: Shows data type, role, scale, descriptive statistics, normality tests, and correlations with other variables Model: Displays type, training dataset, creation date, status (via has_status), performance metrics, and model parameters Hypothesis: Shows status (via has_status), p-value, creation date, associated tests, and project affiliation Statistical Test: Shows test type, result, p-value, date, variables analyzed, and hypotheses tested Status: Shows all entities assigned this status value, organized by entity type Priority: Shows all entities assigned this priority value, organized by entity type Other Entity Types: Shows basic entity information and observations
Status and Priority Information: All entity displays include status information when available via has_status relations Priority assignments are shown for research tasks and other prioritized elements Valid status values include: active, completed, pending, abandoned Valid priority values include: high, low
Sequential Process Relationships: Entity displays show preceding and following entities through precedes relations Process sequences are visualized to show workflow between research activities Research phases and activities display their position in the overall analytical pipeline Sequential relationships help understand dependencies in multi-step analysis processes
Return information: Formatted markdown text with hierarchical structure Sections adapted to the specific entity type Related entities shown with their statistical properties Status and priority information prominently displayed Sequential relationships clearly indicated Error messages if the entity doesn't exist or can't be retrieved
You should: Specify the exact entity name for accurate retrieval Provide the entity type when possible for optimally formatted results Start with project entities to get a high-level overview of research Examine dataset context to understand variable relationships Review variable context to understand distributions and correlations Use hypothesis context to assess research question outcomes Explore model context to evaluate predictive performance Examine statistical test context to understand analysis results Check status entities to see all research elements at the same stage Review priority entities to identify critical research tasks Explore sequential relationships to understand analysis workflows After retrieving context, follow up on specific entities of interest Use in conjunction with startsession to maintain session tracking Remember that this tool only retrieves existing information; use buildcontext to add new entities
|
| endsession | A multi-stage tool for documenting quantitative research sessions, recording statistical analyses, tracking dataset updates, and creating a structured record of research evolution. When to use this tool: Concluding a quantitative research analysis session Documenting updates to datasets and variables Recording new statistical analyses and test results Tracking creation of data visualizations Documenting hypothesis test results and conclusions Updating statistical model performance information Creating a structured record of research activities Establishing a formal conclusion to a focused research period Building a historical record of project development Documenting observations and insights from statistical analysis Updating status values for research activities and entities Assigning or modifying priority levels for research tasks Establishing or modifying sequential relationships between research processes
Key features: Provides a structured, multi-stage workflow for research session documentation Records dataset updates in the knowledge graph Captures new statistical analyses and their results Tracks creation of data visualizations and their purposes Documents hypothesis test outcomes with statistical significance Updates statistical model performance metrics Updates project status information Maintains session continuity with unique session IDs Supports revision of previous stages when needed Offers a comprehensive assembly stage that consolidates all session information Manages status progression of research activities Tracks priority assignments for research tasks Documents sequential relationships between research processes
The endsession tool uses a sequential, multi-stage approach with 9 typical stages: Summary Stage: Records basic session information Dataset Updates Stage: Documents changes to datasets New Analyses Stage: Records new statistical tests performed New Visualizations Stage: Documents visualizations created Hypothesis Results Stage: Records outcomes of hypothesis tests Model Updates Stage: Documents changes to statistical models Status Updates Stage: Records changes to entity status values Project Status Stage: Updates the overall project status Assembly Stage: Consolidates all information and finalizes the session record
Parameters explained: sessionId: Required - Unique identifier for the research session
stage: Required - Current stage of the endsession workflow
Accepts: "summary", "datasetUpdates", "newAnalyses", "newVisualizations", "hypothesisResults", "modelUpdates", "statusUpdates", "projectStatus", or "assembly" Each stage has specific data requirements and processing logic
stageNumber: Required - The sequence number of the current stage
totalStages: Required - Total number of stages planned for this workflow
analysis: Optional - Text analysis or observations for the current stage
stageData: Optional - Stage-specific structured data
nextStageNeeded: Required - Whether additional stages are needed after this one
isRevision: Optional - Whether this is revising a previous stage
revisesStage: Optional - If revising, which stage number is being revised
Status and Priority Management: The statusUpdates stage allows for batch updates to entity status values Valid status values include: active, completed, pending, abandoned Priority assignments (high, low) can be modified in the projectStatus stage Status changes are implemented through has_status relations Priority changes are implemented through has_priority relations Status and priority changes are tracked to maintain research progress history
Sequential Process Management: The projectStatus stage allows for defining or modifying sequential relationships The precedes relation is used to establish logical ordering between research processes Sequential updates help maintain a coherent research workflow Process sequences can be visualized through the loadcontext tool Critical research sequences are maintained to ensure methodological integrity
When the endsession workflow completes (assembly stage with nextStageNeeded: false), the tool performs these updates: Dataset Entities: Updates existing datasets or creates new dataset entities with the provided information Statistical Analyses: Creates entities for statistical tests and links them to projects and variables Visualizations: Creates entities for data visualizations and links them to datasets and projects Hypothesis Updates: Updates existing hypotheses or creates new hypothesis entities with test results Model Updates: Updates existing model entities or creates new models with performance metrics Status Updates: Updates entity status values through has_status relations Priority Updates: Updates entity priority values through has_priority relations Sequence Updates: Updates sequential relationships through precedes relations Project Status: Updates the project status, adds an updated timestamp, and records observations
Return information: JSON response with the following structure when stages are in progress: success: Boolean indicating whether the operation succeeded stageCompleted: The stage that was just completed nextStageNeeded: Whether more stages are required stageResult: The processed result of the current stage
Formatted markdown text summary when the session is completed, including:
You should: Complete all stages in order for comprehensive session documentation Provide specific details in each stage for accurate research documentation Specify dataset updates with clear size, variable count, and status information Include p-values and variable names for statistical analyses Connect visualizations to specific datasets when possible Document hypothesis test results with evidence and significance levels Include performance metrics when updating statistical models Update entity status using has_status relations with valid status values (active, completed, pending, abandoned) Assign priorities using has_priority relations with valid priority values (high, low) Define process sequences using precedes relations to establish research workflows Include relevant observations for project status updates If making a revision, specify which stage is being revised Only mark nextStageNeeded as false on the final assembly stage Review the final summary message to confirm all session details were recorded properly Use the unique session ID consistently across all stages
|