Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

design_intake

Read-only

Submit design details to determine the appropriate causal analysis method. Provide data, controls, and assignment to receive a method-selection status.

Instructions

Route design facts to a method-selection status.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`needs`	No	needs parameter (Optional[str]).
`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
`controls`	No	Control-variable column names.
`estimand`	No	estimand parameter (Optional[str]).
`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.
`assignment`	No	assignment parameter (Optional[str]).
`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.
`data_topology`	No	data_topology parameter (Optional[str]).
`identification_support`	No	identification_support parameter (Optional[str]).

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

D1.9/5.0

Behavior2/5

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

The annotations declare readOnlyHint=true, so the tool is read-only knowledge, but the description itself adds nothing beyond that. It does not disclose any behavioral specifics (e.g., whether it caches results, requires prior calls, or returns a method recommendation). No contradiction, but the description is too vague to provide meaningful transparency.

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

Conciseness2/5

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

The description is extremely short, but this is under-specification rather than conciseness. It uses one sentence but conveys almost no information, so it does not earn credit for being well-structured or efficient.

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

Completeness1/5

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

Given the tool has 12 parameters, no required fields, and an extensive sibling list, the description is completely inadequate. It does not explain the tool's purpose, when to invoke it, or what the output schema offersholistically. Even though an output schema exists, the description itself provides no grounding context for an agent to select it correctly.

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% for all 12 parameters, so the schema fully documents each parameter. The description does not add any parameter-level meaning, but with full coverage the baseline of 3 is appropriate.

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

Purpose2/5

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

The description 'Route design facts to a method-selection status' contains a verb ('route') and a resource ('design facts'), but it is highly abstract and does not specify what action is performed, what 'design facts' are, or what 'method-selection status' means. It fails to distinguish this tool from the hundreds of siblings in the list.

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

Usage Guidelines1/5

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

There is no indication of when to use this tool, what prerequisites exist, or how it differs from alternatives. The sibling list is large, but the description does not mention any other tool or conditions for selection.

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

Deploy Server