Skip to main content
Glama

honest_did_from_result

Read-only

Compute Rambachan-Roth honest confidence intervals on a fitted DID or event-study result using its betas and sigma, to audit sensitivity to parallel-trends violations.

Instructions

Rambachan-Roth (2023) honest CIs on a fitted DID / event-study result; betas and sigma are read off the result. 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": {
      "result_id": "<result_id>"
    },
    "name": "honest_did_from_result"
  }
}

Input Schema

NameRequiredDescriptionDefault
eNoRelative event time to audit.
alphaNo0.05 = 95% CI.
m_barNoDeviation bound M (optional).
detailNoPayload depth; agent is the fullest.agent
methodNoSD smoothness; RM relative magnitude.SD
data_idNoData handle (d_...) from load_data; replaces data_path.
data_csvNoSmall inline table as CSV text.
as_handleNoCache the fit and return its result_id.
data_pathNoAbsolute path of a data file on the server.
result_idYesHandle to a DID / event-study result.
data_recordsNoSmall inline table as row objects.
max_output_bytesNoResult byte budget (default 262144; 0 = none).

Output Schema

NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

B3.4/5.0
Behavior3/5

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

Annotations already declare readOnlyHint=true and openWorldHint=false, so safety is covered. The description adds the meaningful behavioral fact that no refit occurs — parameters are extracted from the stored result — but says nothing about what the validation tier means for the returned numbers or how the CI behaves when m_bar is omitted.

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?

Two short sentences, front-loaded with the method and the target object. The trailing validation-tier sentence is dense jargon of questionable decision value for a caller, but it does not obscure the main point.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 12-parameter tool this is thin, but most parameters are schema-documented and an output schema exists, so return values need no explanation. The gaps are the unstated relationship to honest_did and the unexplained significance of the validation tier for interpreting results.

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 all twelve parameters are already documented, including m_bar, method, and the data_* inputs. The description adds only the indirect point that result_id is the source of betas/sigma; the baseline of 3 is appropriate when the schema does this much work.

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?

The description names a specific method and output (Rambachan-Roth 2023 honest CIs on a fitted DID / event-study result) and states that betas and sigma come from the existing result rather than being re-estimated. That is enough to separate it from a data-fitting sibling like honest_did, though the alternative is never named explicitly.

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?

"betas and sigma are read off the result" implies the prerequisite that a fitted result_id must already exist, which is useful context. However, there is no explicit when-to-use / when-not-to-use statement, and no pointer to the alternative path for users who only have raw data.

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