Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

pub_ready

Read-only

Assess whether your causal estimates meet target-venue publication standards by verifying balance, placebo, pre-trends, robustness, and sensitivity checks, then list violations and next steps.

Instructions

Publication readiness checklist.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`venue`	No	Target venue: 'top5_econ', 'aej_applied', 'rct'.	top5_econ
`design`	No	Research design: 'rct', 'did', 'rd', 'iv', 'observational'.
`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
`has_mht`	No	Already have MHT correction.
`results`	No	List of estimated result objects.
`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.
`has_balance`	No	Already have balance table.
`has_placebo`	No	Already have placebo tests.
`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.
`has_pretrends`	No	Already have pre-trend tests.
`has_robustness`	No	Already have robustness checks.
`has_sensitivity`	No	Already have sensitivity analysis.
`has_heterogeneity`	No	Already have subgroup analysis.

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

C2.8/5.0

Behavior2/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so the description adds no behavioral context beyond what structured data provides. It does not contradict the annotations, but it also does not disclose what dimensions are checked or how the checklist behaves.

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

Conciseness3/5

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

The description is a single short phrase with no wasted words. However, it is under-specified relative to the tool's 16 parameters and complex sibling context, so it earns a middle score rather than higher.

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 16 optional parameters and many sibling reporting/audit tools, the description does not convey when to use it, what it evaluates, or how it relates to alternatives like audit, preflight, or robustness_report. The output schema exists, but the decision context is largely missing.

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%, with all 16 parameters documented in the input schema itself. The description adds no parameter-level meaning, so the baseline of 3 is appropriate.

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 identifies a clear resource ('publication readiness') and function (checklist), so an agent can infer this tool assesses whether an analysis is ready for publication. It does not explicitly differentiate from sibling audit/preflight/robustness_report tools, which prevents a 5.

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?

There is no guidance on when to use this tool versus the many sibling checking/reporting tools. The name implies an end-of-analysis check, but the description leaves timing and selection to inference.

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

Deploy Server