Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

did_cluster_diagnostics

Read-only

Counts treatment-assigned clusters and grades the count against published staggered DiD simulation evidence, flagging designs at or below 30 clusters where coverage is weak. Also reports clusters per cohort for group-time effects.

Instructions

Count the clusters treatment is assigned at and grade the count against the simulation grid of Ulloa-Perez et al. (2025), who found that at 30 clusters every modern staggered DiD estimator they evaluated under-covered a nominal 95% interval, with coverage improving as clusters accumulated. Thirty is the smallest cell they ran, so fewer clusters is reported as outside their evidence rather than as merely worse. Also reports clusters per cohort, since a group-time effect rests on the clusters in its own cohort. Assumptions: The grading reports what published simulation evidence exists at this cluster count; it is not a power calculation for this design or estimator. Pre-conditions: panel with unit and cohort columns. Failure modes: Cluster column empty or absent -> Check that the cluster column is populated. Alternatives: sp.wild_cluster_bootstrap, sp.ri_test, sp.conley.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`unit`	Yes	Unit identifier
`warn`	No	Warn when the design sits in or below the weakest cell of the reference grid.
`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
`cluster`	No	Level treatment is assigned at (state, provider group, district). Defaults to unit with a warning: the two coincide only under independent unit-level assignment, and assuming so is the optimistic error.
`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.
`first_treat`	Yes	First-treatment period; 0 = never-treated
`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

A4.5/5.0

Behavior5/5

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

The description goes well beyond the readOnlyHint annotation by explaining what the tool reports, how it grades cluster counts, the '30 clusters' boundary behavior, and per-cohort reporting. It also discloses failure modes and assumptions, which is exactly the kind of behavioral context annotations do not capture.

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?

The description is longer than average, but it earns its length with labeled sections for assumptions, pre-conditions, failure modes, and alternatives. The core purpose is front-loaded in the first sentence, and the organization makes the content easy to parse.

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

Completeness5/5

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

Given the tool's complexity, the robust output schema, and the readOnlyHint annotation, the description is complete. It covers what the tool does, how to interpret the grading, preconditions, common failure modes, and alternatives, leaving no critical gap for an agent deciding whether and how to call it.

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 already documents all parameters in detail. The description adds some context around 'cluster column' and 'unit and cohort columns', but it does not materially extend the parameter semantics beyond what the schema provides.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description starts with a specific, active behavior: 'Count the clusters treatment is assigned at and grade the count against the simulation grid', and then explains the citation and evidence basis. It also names alternatives at the end, so an agent can distinguish this diagnostic tool from related inference tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides explicit assumptions, pre-conditions, failure modes, and a list of alternatives. It clearly says the tool is not a power calculation, which helps prevent misuse. However, it does not give conditions for choosing between this tool and its named alternatives, so the routing guidance is slightly incomplete.

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

Deploy Server