Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

auto_did

Read-only

Run staggered difference-in-differences estimators (CS, SA, BJS) side by side to compare treatment-effect estimates and diagnostics across methods.

Instructions

Run several staggered-DiD estimators side by side.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`g`	Yes	First-treatment-period column (0 or NaN for never-treated).
`i`	Yes	Unit identifier column.
`t`	Yes	Calendar time column.
`x`	No	Covariates (used by CS / SA / BJS where supported).
`y`	Yes	Outcome column.
`alpha`	No	Significance level for reported CIs.
`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
`methods`	No	Subset of ``{'cs', 'sa', 'bjs'}``. Defaults to all three.
`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.
`select_by`	No	How to pick the winner. ``'median'`` returns the candidate with the median point estimate across successes. A method name returns that specific candidate (useful for forcing a baseline).	median
`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

B3.1/5.0

Behavior3/5

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

Annotations declare readOnlyHint=true, so the description doesn't need to cover safety. The description adds no behavioral context beyond the schema, such as how 'side by side' manifests in output or whether results are cached. With annotations already covering the safety profile and an output schema present, a neutral score is appropriate.

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, focused sentence that front-loads the core purpose. It avoids fluff and is appropriately terse given the rich schema. It could be slightly more informative about usage, but for conciseness it earns a high score.

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?

Despite the presence of an output schema, the description is too brief for a tool with 14 parameters and multiple estimation methods. It fails to explain when to prefer this over running estimators individually, how to interpret the 'side by side' comparison, or what the 'agent' detail level entails. For such a complex tool, a one-sentence description is inadequate.

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 all 14 parameters are documented in the input schema. The description adds no additional parameter semantics beyond what the schema provides. Baseline 3 is correct when the schema carries the parameter documentation burden.

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 clear verb and resource: 'Run several staggered-DiD estimators side by side.' It conveys that the tool compares multiple estimators, which distinguishes it from single-estimator siblings like 'did' or 'staggered_cs'. However, it doesn't explicitly name those alternatives or the specific estimators (cs, sa, bjs) beyond what the schema provides, so it stops short of full differentiation.

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?

The description provides no guidance on when to use this tool versus alternatives. It doesn't mention that it should be used when comparing multiple staggered DiD estimators, or that it supersedes running them individually. With dozens of DiD-related siblings, the lack of usage context leaves the agent to infer applicability from the schema alone.

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

Deploy Server