melly_decompose

Read-only

Decompose outcome differences between groups with quantile regression. Quantify covariate and coefficient effects at each quantile using the Melly (2005) method.

Instructions

Melly (2005) quantile decomposition.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	Yes	Primary running variable, regressor, or feature input for this estimator.
`y`	Yes	Outcome variable column name or outcome array.
`group`	Yes	Group or cohort identifier.
`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
`n_tau_qr`	No	Number of tau qr.
`tau_grid`	No	Grid of tau values to evaluate.
`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	Same convention as ``machado_mata``: ``reference=0`` uses A's beta on B's X (coefficient-swap counterfactual F_{Y<0\|1>}), opposite to ``dfl_decompose`` whose ``reference=0`` uses A's X with B's beta.
`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

C2.2/5.0

Behavior2/5

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

With readOnlyHint=true, the safety profile is already known, so the bar is lower. However, the description adds no behavioral context beyond the label—no mention of what quantities are produced, how the reference convention affects results, or what assumptions matter. It does not contradict the annotations, but it also adds nothing beyond them.

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, which is superficially concise, but for a 12-parameter tool with a large sibling family this is under-specification rather than deliberate conciseness. A one-line label does not earn its place as an adequate tool description.

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?

The schema is rich and an output schema exists, but the top-level description is too thin to support tool selection among dozens of decomposition-related siblings. An agent cannot tell from this description what problem it solves, when to prefer it, or what its output represents without relying entirely on external knowledge of Melly (2005).

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 input schema provides detailed meaning for every parameter, including the reference convention and payload-depth options. The description itself contributes no parameter semantics, so the baseline 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 is essentially a tautological label: 'Melly (2005) quantile decomposition' restates the tool name with a citation. It never states the action or resource explicitly (e.g., 'decomposes the outcome gap across quantiles') and does not distinguish it from the many sibling decomposition tools such as dfl_decompose or machado_mata.

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?

No top-level guidance says when to use this tool instead of alternative decomposition methods. The only hint of alternatives appears deep in the 'reference' parameter description, which contrasts conventions with machado_mata and dfl_decompose; that is useful for a parameter choice but not for selecting the tool itself.

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

Deploy Server

Causal Decision Agent