Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rd_compare

Read-only

Compare multiple regression discontinuity estimators on the same dataset to assess robustness and choose the best approach.

Instructions

Compare multiple RD estimators on the same data.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	c parameter (float).
`x`	Yes	Primary running variable, regressor, or feature input for this estimator.
`y`	Yes	Outcome variable column name or outcome array.
`alpha`	No	Confidence level forwarded to each estimator that accepts ``alpha``.
`fuzzy`	No	Fuzzy treatment column passed through to all methods that accept it.
`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	Method aliases recognised by the :data:`sp.rd._RD_METHOD_ALIASES` dispatcher. Default: ``('rdrobust', 'honest', 'randinf')``.
`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.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
`method_kwargs`	No	Per-method extra kwargs, e.g. ``{'rdrobust': {'kernel': 'uniform'}}``.

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

C2.9/5.0

Behavior2/5

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

Annotations declare readOnlyHint=true and openWorldHint=false, so the description carries a lower bar for safety disclosure. However, the description adds no behavioral context beyond the purpose: it doesn't mention that it returns a comparison table, that results can be cached via as_handle, or any performance characteristics. The read-only nature is consistent with annotations, but the description itself adds minimal value.

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 a single sentence, highly concise, and front-loaded with the main action. There is zero wasted text, making it appropriately sized for a one-line summary.

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?

Given the tool has 13 parameters, an output schema, and rich sibling context, the description is too sparse. It fails to convey when to use this tool vs alternatives, what output to expect, or any behavioral notes. The schema and annotations carry most of the burden, but the description should provide contextual guidance, which it lacks.

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?

The schema has 100% coverage for all 13 parameters, each with detailed descriptions, so the baseline is 3. The description does not mention any parameters or add meaning beyond the schema. It neither compensates for gaps (there are none) nor provides extra insight into parameter usage.

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 (compare) and resource (multiple RD estimators) on the same data, which is specific and distinguishes it from single-estimator tools like rdrobust. However, it doesn't mention which estimators or that it defaults to three methods, though that is covered in the schema. It's not a tautology and gives a clear purpose.

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 is for comparing multiple estimators rather than a single estimation, nor does it reference any sibling tools or exclusion criteria. The agent is left to infer usage context.

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

Deploy Server