StatsPAI

vcov_from_result

Read-only

Recompute standard errors for a cached fit under a different VCE (robust, HC3, cluster), refitting with only vce= changed and returning a new result or a side-by-side ratio table.

Instructions

Standard errors of a cached fit (result_id) under another vce: re-runs the fit's own call with only vce= changed, so the SEs equal a direct refit. One vce returns the new result; a list returns a side-by-side table with the ratio to the fitted SE.

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>",
      "vce": "<vce>"
    },
    "name": "vcov_from_result"
  }
}

Input Schema

Name	Required	Description	Default
`vce`	Yes	Stata-style request ('robust', 'hc3', 'cluster state', 'cluster state year') or a list of them.
`terms`	No	Table: keep only these coefficients.
`detail`	No	Payload depth; agent is the fullest.	agent
`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`	Yes	Handle to a fit from an estimator with vce=.
`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

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, and the description adds genuinely non-obvious behavior: the tool re-executes the fit's own call with only vce= changed, so results are guaranteed equal to a direct refit, and the return shape differs depending on whether one vce or a list is passed. It does not mention compute cost or that caching may occur (see as_handle), which keeps it from 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.

Conciseness5/5

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

Two sentences with zero waste: the core action and its equivalence guarantee come first, then the input-shape/return-shape mapping. Every clause carries information an agent needs.

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 and rich field descriptions, the description need not explain return payloads, and it correctly focuses on behavior and the single-vs-list branching. The one residual gap is why a caller supplying result_id would also use data_path/data_id/data_csv — a plausibility question an agent may have — but that is a minor omission given full schema coverage.

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; the description earns the extra point by explaining the semantic consequence of the vce parameter's polymorphic type — a single value yields a new result, a list yields a side-by-side table with the ratio to the fitted SE. It adds no detail on terms, detail, or the data_* parameters, which the schema already covers.

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?

States a specific verb and resource: computes standard errors of a cached fit under a different vce. The parenthetical '(result_id)' anchors the required input, and the phrase 'cached fit' distinguishes it from sibling refit tools such as honest_did_from_result or sensitivity_from_result.

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?

Makes the triggering condition clear — you have a cached fit and want different VCEs without a manual refit — and implicitly excludes cases where no result_id exists. It does not name an explicit alternative or a when-not-to-use case, 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.