Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

sensitivity_dashboard

Read-only

Run multi-dimensional sensitivity analysis on a baseline causal estimate, testing dimensions, significance levels, and subsamples to return diagnostics and next steps.

Instructions

Comprehensive multi-dimensional sensitivity analysis.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`alpha`	No	Significance level for confidence intervals and tests.
`detail`	No	Payload depth: 'minimal' (~150 tokens) for sub-step calls where only the point estimate is needed; 'standard' (~1K tokens) for diagnostics + coefficient table; 'agent' (~2K tokens, default) adds violations / next_steps / suggested_functions so the LLM can plan its next call without another round-trip.	agent
`result`	Yes	Baseline estimated result.
`verbose`	No	verbose parameter (bool).
`as_handle`	No	If true, cache the fitted result on the server and return result_id + result_uri alongside the JSON payload so a subsequent tools/call can chain without re-running.
`data_path`	No	Absolute path or URL to a data file. Supported: .csv / .tsv / .txt (delimited), .parquet / .pq, .feather / .arrow, .xlsx / .xls, .dta (Stata), .json / .jsonl. Schemes: file://, s3://, gs://, https://.
`result_id`	No	Optional handle to a previously-fitted result (returned by an earlier call when as_handle=true). Tools that operate on a fitted object accept this in place of re-supplying data_path + columns.
`dimensions`	No	Which dimensions to test. Default: all applicable.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

D1.9/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the read-only nature is covered. However, the description adds nothing beyond that – no mention of caching via as_handle, data loading requirements, or what the 'multi-dimensional' aspect entails. The description contributes no behavioral detail beyond the structured annotations.

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

Conciseness2/5

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

The description is a single sentence, which is short, but it is under-specified rather than concise. It does not front-load any actionable information and fails to convey the tool's scope or behavior, making it unhelpful despite its brevity.

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?

For a tool with 10 parameters and a complex sensitivity-analysis purpose, the description is woefully incomplete. It omits what the output looks like, how 'dimensions' are specified, how the tool interacts with data_path vs result_id, and what distinguishes it from other sensitivity tools. The schema documents parameters but not the tool's overall workflow.

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% with rich descriptions for parameters like detail (with enum and token sizes), as_handle (caching behavior), and data_path (supported formats). The description adds no parameter-level meaning beyond what the schema already provides, so the baseline of 3 is appropriate.

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 'Comprehensive multi-dimensional sensitivity analysis' is vague; it states the general topic but lacks a specific verb+resource, and it does not differentiate from numerous sibling tools like 'sensitivity', 'unified_sensitivity', or 'sensitivity_from_result'. It reads as a restatement of the tool's name rather than a clear functional definition.

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?

No guidance is provided on when to use this tool versus alternatives. With many sensitivity-related siblings (e.g., 'sensitivity_plot', 'synth_sensitivity', 'dml_sensitivity'), the description offers no conditions or exclusions to help the agent choose correctly.

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

Deploy Server