Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

calibrate_confounding_strength

Read-only

Calculate the unobserved-confounder strength required to shift a causal estimate to a target value, supporting sensitivity checks.

Instructions

Calibrate the strength of an unobserved confounder required to

Input Schema

TableJSON Schema

Name	Required	Description	Default
`se`	Yes	se parameter (float).
`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
`estimate`	Yes	estimate parameter (float).
`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.
`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.
`target_estimate`	No	Effect value to explain away.
`observed_r2_outcome`	Yes	Partial-R2 of the observed covariate(s) with Y (resp. D). Used to benchmark "1x as confounding as observed" / "2x" etc.
`observed_r2_treatment`	Yes	Partial-R2 of the observed covariate(s) with Y (resp. D). Used to benchmark "1x as confounding as observed" / "2x" etc.

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

D1.7/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true, so the agent knows it is a read-only computation. The description adds nothing beyond that, not even that it takes a fitted result or data path, or how as_handle caching works. It does not contradict annotations, but it also fails to disclose any behavioral nuance beyond what annotations already provide.

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

Conciseness1/5

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

The description is a single incomplete sentence that ends abruptly. This is not conciseness but under-specification; it provides no usable structure and fails to deliver a complete thought.

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 12 parameters and a sensitivity-analysis purpose, this description is grossly incomplete. Even though an output schema exists, the agent cannot know the full purpose, what the tool returns, or how to chain it with other tools. The truncated text makes the definition nearly unusable.

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%, so all 12 parameters are documented in the schema. The description adds no parameter-specific meaning, and with high coverage the baseline of 3 is appropriate. The truncated description doesn't help clarify which parameters are essential or how they interact.

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 starts with a clear verb and resource ('Calibrate the strength of an unobserved confounder') but is truncated mid-sentence ('required to'), leaving the purpose incomplete. It does not fully state what the tool does or how it differs from the many sensitivity-related siblings (sensemakr, oster_bounds, sensitivity).

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?

There is no guidance on when to use this tool versus alternatives, no prerequisites (e.g., needing a fitted model or result_id), and no exclusionary statements. The description is a fragment and gives no usage context.

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

Deploy Server