Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

synth_donor_sensitivity

Read-only

Run a donor-pool bootstrap to test how synthetic-control estimates change across random donor subsets, revealing sensitivity and stability.

Instructions

Donor-pool bootstrap sensitivity for Synthetic Control.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`k`	No	Donor subset size. Default is ``floor(J * 0.75)`` where J is the total number of donors.
`seed`	No	Random seed for reproducibility.
`time`	Yes	Time column.
`unit`	Yes	Unit identifier column.
`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
`outcome`	Yes	Outcome variable.
`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`	Yes	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://.
`n_samples`	No	Number of random donor subsets to draw.
`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.
`penalization`	No	Ridge penalty forwarded to SCM.
`treated_unit`	Yes	Identifier of the treated unit.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`treatment_time`	Yes	First treatment period.

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

B3.1/5.0

Behavior3/5

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

The description adds the methodology detail 'bootstrap', which is slightly beyond the tool name, and the readOnlyHint=true annotation already communicates that this is a safe read-only computation. However, it does not disclose the stochastic sampling behavior, what is returned, or how the sensitivity results should be interpreted. It does not contradict the annotations.

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 a single short phrase with no filler and is easy to scan. It could be improved by using a full sentence with a verb, but as a concise summary it earns its place.

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?

For a tool with 15 parameters, 6 required parameters, and many closely related sibling tools, the description is too thin. It does not explain what 'sensitivity' means here, what kind of result the user should expect, or when this tool is the right choice. The output schema covers return structure, but the surrounding context is still insufficient for reliable selection among many synth and sensitivity tools.

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%, so the parameters are already well documented in the schema. The description adds no parameter-level meaning beyond the general idea of donor-pool bootstrap sensitivity, which maps loosely to k and n_samples, but that is already explicit in the schema.

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 names a specific resource and method: donor-pool bootstrap sensitivity for Synthetic Control. It is more specific than generic siblings like synth_sensitivity, but it is a noun phrase rather than a verb phrase ('Runs...', 'Computes...'), so it stops short of a fully explicit action.

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?

No guidance is given on when to use this tool instead of synth_sensitivity, robust_synth, synth_power_plot, or other sensitivity-related siblings. There is no mention of use cases, exclusions, or alternative tools, leaving the agent to infer applicability from the name alone.

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

Deploy Server