synth_sensitivity

Read-only

Run all synthetic control sensitivity diagnostics in a single call to check how causal estimates change with donor subsets, penalization, and significance levels.

Instructions

Run all SCM sensitivity diagnostics in a single call.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`seed`	No	Random seed.
`time`	Yes	Time column.
`unit`	Yes	Unit identifier column.
`alpha`	No	Significance level.
`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://.
`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.
`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.
`n_donor_samples`	No	Number of random donor subsets for donor sensitivity.

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

A3.5/5.0

Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the safety profile is covered and no contradiction exists. The description adds only the 'single call' batching trait; meaningful behavioral context (payload depth, token sizes, violations/next_steps/suggested_functions) lives in the detail parameter schema, not the description. Given annotation coverage, the description contributes minimally but adequately.

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

Conciseness5/5

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

A single front-loaded sentence with zero filler. It states the action, the resource, and the distinguishing scope ('in a single call') — nothing extraneous earns its place.

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

Completeness3/5

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

With an output schema present, a rich 100%-covered parameter schema, and annotations covering the read-only profile, the one-line description is nearly sufficient. However, it does not state what 'sensitivity diagnostics' actually includes, which an agent would need to anticipate output size or decide between this and the many sibling 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 schema documents all 15 parameters well, including rich descriptions for detail (token sizes), data_path (formats/schemes), and as_handle (caching). The tool description itself adds no parameter meaning, but the schema carries the full burden, 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 ('Run') and resource ('all SCM sensitivity diagnostics') with a scoping claim ('in a single call') that differentiates it from single-diagnostic siblings like synth_donor_sensitivity, synth_loo, and synth_time_placebo. It is clear but does not enumerate which diagnostics are bundled, leaving the agent to infer scope from the name.

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 only implied: 'in a single call' signals using this instead of running individual sensitivity tools, and the detail parameter (in schema) routes sub-step vs agent usage. However, the description never names alternatives explicitly or states when NOT to use this tool, relying on the reader to connect it to the sibling family.

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

Deploy Server

Causal Decision Agent