StatsPAI

route_estimator

Read-only

Routes a research question to matching estimator functions: pick an estimator family, answer its decision questions, and get example calls, assumptions, and guide sections—no data needed.

Instructions

Route a research question to estimator calls without data. Give the family (did / iv / rd / matching / ml_causal / qte / dynamic_panel) and answers to its decision questions; get the matching registered functions with example calls, why each is right, the assumptions it adds and the guide section to read, plus the unanswered questions and the one that narrows the choice most. Call with no answers to see the questions. The full guide is readable at statspai://guide/{family}.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "family": "<family>"
    },
    "name": "route_estimator"
  }
}

Input Schema

Name	Required	Description	Default
`detail`	No	Payload depth; agent is the fullest.	agent
`family`	Yes	Estimator family.
`answers`	No	question_key -> answer (see the questions returned when omitted).
`data_id`	No	Data handle (d_...) from load_data; replaces data_path.
`data_csv`	No	Small inline table as CSV text.
`as_handle`	No	Cache the fit and return its result_id.
`data_path`	No	Absolute path of a data file on the server.
`result_id`	No	Handle of an earlier fit made with as_handle=true.
`data_records`	No	Small inline table as row objects.
`max_output_bytes`	No	Result byte budget (default 262144; 0 = none).

Output Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Nov 12, 2026

TDQS

A4.3/5.0

Behavior4/5

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

Annotations only declare readOnlyHint=true and openWorldHint=false, so the description carries most of the behavioral load and does so well: it discloses that the result includes ranked functions, reasons, added assumptions, a guide section, the unanswered questions and the single most discriminating question. It never describes what happens on an unrecognized family or whether partial answers degrade the ranking, which keeps it short of a 5.

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

Conciseness4/5

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

Three sentences, front-loaded with the purpose and payload before the operational hint and the guide URI, so the agent gets the essential framing immediately. The middle sentence is long and stacks four payoff items, but each item is informative rather than filler.

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?

For a ten-parameter tool with an output schema, the description covers the routing purpose, the discovery loop and the return payload, and the output schema removes the need to spell out return values. The remaining gap is that the schema carries data_id, data_path, data_csv, data_records, result_id, as_handle and max_output_bytes while the description frames the tool as working 'without data', leaving it unclear whether supplying data is supported or pointless.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100%, so the baseline is 3, but the description adds meaning the schema cannot: it explains that 'answers' is a question_key -> answer map whose keys are discoverable by omitting answers entirely, which is the key procedural insight for that nested object. It adds nothing for detail, as_handle, max_output_bytes or the data_* handles, which the schema covers adequately.

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 opens with a specific verb-plus-resource: route a research question to estimator calls, explicitly 'without data', which separates it from the data-fitting siblings (did, iv, feols, ivreg) that actually estimate. It also enumerates the concrete payload (matching registered functions, example calls, assumptions, guide section), so an agent knows exactly what class of tool this is before opening any schema.

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 gives clear operational guidance for a two-step workflow: 'Call with no answers to see the questions' first, then supply the family plus answers to get narrowed candidates. That tells the agent how to begin when it does not yet know the question keys. It does not, however, say when to skip this tool and go straight to a concrete estimator sibling or to a design-detection tool, so no true exclusions are stated.

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