Causal Decision Agent

by vikranthviki

Overview Schema Source Related Servers Discussions Admin

Python

Local

did_summary_to_markdown

Read-only

Render a did_summary analysis result as a GitHub-Flavoured Markdown table for clear reporting and sharing.

Instructions

Render a :func:did_summary result as a GitHub-Flavoured Markdown table.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`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
`digits`	No	Decimal precision for numeric columns.
`result`	Yes	Output of :func:`did_summary`.
`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.
`include_ci`	No	Include the 95 % CI column.
`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.
`include_breakdown`	No	Include the Rambachan-Roth breakdown M* column (CS row only, blank for others). Ignored if sensitivity was not requested.

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

A4/5.0

Behavior3/5

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

The readOnlyHint annotation already establishes that this is non-destructive, and the description adds that this is a formatting/rendering operation rather than a modeling operation. It does not detail the returned payload or file-writing behavior, but for a read-only renderer the annotations lower the burden.

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?

A single, front-loaded sentence with no filler; the verb, input, and output format are all present. Nothing could be removed without losing meaning.

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

Completeness4/5

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

With a rich input schema, an output schema, and a readOnlyHint annotation, the description does not need to explain return values or safety. It states the tool's role clearly, though it could optionally note that this is the Markdown-specific sibling of did_summary_to_latex.

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 schema already documents all 10 parameters, including the required `result` and the `detail`/`digits` formatting options. The description only restates that `result` comes from did_summary, adding no new parameter-level semantics beyond the schema.

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 names a specific verb ('Render'), a precise input (a :func:`did_summary` result), and an exact output format (GitHub-Flavoured Markdown table). This is enough to distinguish it from siblings like did_summary_to_latex and did_summary_plot, even though no sibling is named explicitly.

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

Usage Guidelines4/5

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

It clearly implies the correct context: after obtaining a did_summary result, use this tool when a Markdown table is wanted. It does not explicitly name alternatives or exclusions, but the output-format qualifier gives the agent the main selection cue.

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

Deploy Server