StatsPAI

spec_curve

Read-only

Enumerates defensible model-choice combinations, runs every specification, and returns sign and magnitude distributions so agents can report robustness across a researcher-degree-of-freedom multiverse.

Instructions

Specification-curve analysis (Simonsohn et al. 2020): enumerates every combination of model choices the user declares defensible, runs them all, and returns the sign/magnitude distribution. Use when an agent needs to report robustness across a researcher-degree-of-freedom multiverse. Validation: validated evidence tier (known-truth, reference, external-parity, or Monte Carlo artifact).

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": {
      "x": "<x>",
      "y": "<y>"
    },
    "name": "spec_curve"
  }
}

Input Schema

Name	Required	Description	Default
`x`	Yes	Focal regressor (treatment) column.
`y`	Yes	Outcome column.
`alpha`	No
`detail`	No	Payload depth; agent is the fullest.	agent
`data_id`	No	Data handle (d_...) from load_data; replaces data_path.
`controls`	No	The multiverse of control sets: a list of control-column lists, one per specification.
`data_csv`	No	Small inline table as CSV text.
`se_types`	No	Standard-error flavours to sweep (e.g. 'classical', 'hc1', 'cluster').
`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.
`cluster_var`	No	Cluster column for clustered SEs.
`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

A4.1/5.0

Behavior4/5

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

Annotations only declare readOnlyHint and openWorldHint, so the description carries most of the load and does add real context: it explains the exhaustive enumeration behavior, the shape of the return (sign/magnitude distribution), and a validation/evidence-tier claim. It omits practical behavior such as compute cost of running the full multiverse and how data handles like result_id or as_handle affect reuse.

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 compact sentences, front-loaded with the method and its output shape before the usage hint. The trailing 'Validation:' clause is terse but scoped; nothing is 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?

With 14 parameters, an output schema, and safety annotations, the description supplies the method, the output shape, the usage trigger, and a validation guarantee. What is missing is operational context such as cost/time of sweeping many specifications and how the multiverse inputs relate to data handles, but that is secondary given the rich schema.

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 93%, so the schema already documents parameters like controls, se_types, detail, and as_handle thoroughly. The description's contribution is conceptual framing ('model choices the user declares defensible') rather than added syntax or constraint detail, so baseline 3 applies.

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 method (specification-curve analysis, cited to Simonsohn et al. 2020), states the concrete operation (enumerate every defensible model-choice combination, run them, return a sign/magnitude distribution), and its multiverse framing distinguishes it from siblings like cross_validate or audit.

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 an explicit when-to-use condition: report robustness across a researcher-degree-of-freedom multiverse. It does not name a specific sibling alternative or state when not to use it (e.g. versus cross_validate or bacon_decomposition), so it stops short of full routing guidance.

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