Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

contrast

Read-only

Compare predictive margins across levels of a categorical variable using a fitted model, producing validated contrasts for evidence-based decisions.

Instructions

Compute contrasts of predictive margins across levels of a variable. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

Input Schema

TableJSON Schema

Name	Required	Description	Default
`alpha`	No	Significance level.
`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
`method`	No	Contrast type: - ``'r'`` (reference): each level vs reference level. - ``'ar'`` (adjacent): each level vs the previous level. - ``'gw'`` (grand-mean weighted): each level vs the weighted grand mean of all levels.	r
`result`	Yes	Fitted model result.
`variable`	Yes	Categorical variable whose levels are contrasted.
`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://.
`reference`	No	Reference level when ``method='r'``. Defaults to the smallest observed level.
`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

B3.2/5.0

Behavior2/5

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

With readOnlyHint=true, the safety profile is covered by annotations, but the description adds little behavioral context. The cryptic validation sentence ('validated evidence tier...') is not clearly behavioral and does not explain what the tool returns, how it chains with fitted results, or how as_handle affects behavior.

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 first sentence is concise and useful, but the second sentence is a disjointed fragment that reads as metadata rather than guidance, meaning not every sentence earns its place. Overall the description is short but contains unnecessary ambiguity.

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 detailed parameter schema and existing output schema, the description omits critical context for a post-estimation tool: it does not state that a fitted model result is required, how it relates to 'margins', or any chaining/prerequisite behavior. An agent might not know how to invoke this correctly after obtaining margins.

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 baseline is 3. The description does not add meaning beyond the schema; it only loosely aligns with the 'variable' parameter by mentioning 'levels of a variable', but provides no extra semantics.

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 uses a specific verb ('Compute') and names the precise output ('contrasts of predictive margins across levels of a variable'). It clearly distinguishes this from related tools like 'margins' by focusing on contrasts, and the scope is explicit.

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

Usage Guidelines3/5

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

Usage is only implied: an agent can infer this tool is for contrasting predictive margins across levels, but there is no explicit guidance on when to prefer it over alternatives such as margins, pwcompare, or lincom, nor any stated prerequisites or exclusions.

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

Deploy Server