StatsPAI

interpret_result

Read-only

Generates a plain-language interpretation of a fitted result’s estimate, uncertainty, and identification limits, tailored to researcher, policymaker, or general audiences.

Instructions

Natural-language interpretation of a fitted result (result_id): the estimate, its uncertainty and what the design does / does not identify, grounded in the result's own numbers. Uses the client's model via MCP sampling when advertised (no API key); otherwise returns a deterministic structured brief, never an invented narrative.

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": {
      "result_id": "<result_id>"
    },
    "name": "interpret_result"
  }
}

Input Schema

Name	Required	Description	Default
`detail`	No	Payload depth; agent is the fullest.	agent
`data_id`	No	Data handle (d_...) from load_data; replaces data_path.
`audience`	No	Tone / depth: 'researcher' (precise, names identification assumptions), 'policymaker' (plain, decision-focused), 'general' (no jargon).	researcher
`data_csv`	No	Small inline table as CSV text.
`question`	No	Optional specific question to focus the interpretation (e.g. 'is the effect economically meaningful?').
`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`	Yes	Handle to a previously-fitted result.
`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

A3.8/5.0

Behavior4/5

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

Goes well beyond the readOnlyHint/openWorldHint annotations by disclosing two execution paths: MCP sampling through the client's model when available, and a deterministic structured brief otherwise. The guarantee 'never an invented narrative' and the 'grounded in the result's own numbers' constraint are exactly the behavioral context an agent needs; it stops short of noting sampling cost or latency.

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?

Two compact sentences with zero filler: what is produced first, then the sampling/fallback behavior. Every clause carries information an agent would otherwise have to guess.

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 an output schema present, the description needn't explain return values, and it correctly focuses on the sampling-vs-fallback contract. For a read-only interpretation tool with 10 fully documented parameters this is nearly complete; only a note on the runtime cost or the interaction with question/audience would close the gap.

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 detail, audience, question, max_output_bytes and the data_* handles are already documented. The description reinforces result_id and the 'specific question' focus only implicitly via the identification question, adding little meaning beyond the schema. Baseline 3 fits.

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

Purpose4/5

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

Names a specific verb-and-resource pair: natural-language interpretation of a fitted result identified by result_id, covering the estimate, its uncertainty and identification limits. It is clear what the tool produces, but it never names an alternative (e.g. brief_result, audit_result) so the boundary against similar siblings is left to inference.

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: the tool takes a result_id from a prior fit and returns an interpretation. The 'when advertised (no API key)' clause describes a runtime condition, not a selection rule, and there is no explicit when-not guidance or named alternative for getting a plain structured summary instead.

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