Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

rd_dashboard

Read-only

Generate a four-panel RD diagnostic dashboard to check cutoff validity, bandwidth sensitivity, covariate balance, and treatment effects, then identify assumption violations for rollout decisions.

Instructions

Four-panel RD diagnostic dashboard.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`c`	No	Cutoff.
`h`	No	Reference bandwidth used for plotting and as the basis for ``bw_grid``. If None, MSE-optimal bandwidth from rdrobust.
`x`	Yes	Primary running variable, regressor, or feature input for this estimator.
`y`	Yes	Outcome variable column name or outcome array.
`covs`	No	Covariates for the balance panel. If None, the panel shows the density's binomial near-cutoff test instead.
`save`	No	If a path is given, also save the figure (extension determines format).
`fuzzy`	No	Fuzzy treatment column (passed through to RD plot/sensitivity).
`title`	No	Suptitle.
`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
`bw_grid`	No	Bandwidths to evaluate in the sensitivity panel. If None, uses ``[0.5, 0.75, 1.0, 1.25, 1.5, 2.0] x h_mse``.
`figsize`	No	figsize parameter (Tuple[float, float]).
`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.

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

C2.5/5.0

Behavior2/5

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

The annotations already provide the safety profile (readOnlyHint, openWorldHint), so the description's 'four-panel diagnostic dashboard' adds only a minimal output trait. It doesn't say what the four panels are, whether it renders a figure or payload, or that a 'save' path triggers file writing, leaving key behavioral traits undisclosed.

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 economical and the core phrase is front-loaded, with no filler. But it is under-specified for a 16-parameter dashboard tool rather than appropriately concise, so brevity is achieved at the expense of useful content.

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 rich schema and output schema, the top-level description is too thin for a complex tool with this many sibling alternatives. It omits usage conditions, the identities of the four panels, and behavior beyond 'dashboard', leaving the agent without enough context to invoke or chain it confidently.

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% and the parameter descriptions are detailed (e.g., 'detail' payload modes, data_path formats), so the baseline applies. The tool description contributes no parameter-level meaning beyond what the schema already documents.

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

Purpose3/5

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

The description identifies the tool as a diagnostic dashboard for RD analyses and adds the 'four-panel' detail. However, it is a noun phrase with no explicit verb, doesn't enumerate the panels, and doesn't distinguish rd_dashboard from other RD diagnostic/plot tools in the large sibling set.

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 rd_dashboard versus rdplot, rdrobust, rdsummary, rdrobustness_table, or other RD siblings. 'Diagnostic dashboard' implies a high-level use case, but the agent is left to infer the selection criteria and no exclusions are stated.

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

Deploy Server