Skip to main content
Glama
vikranthviki

Causal Decision Agent

by vikranthviki
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Local

verify_benchmark

Read-only

Validate causal estimates against built-in data-generating processes with known true effects, producing diagnostics and actionable next steps for reliable decisions.

Instructions

Run verify against built-in DGPs with known true effects.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
seedNoBase seed. Per-rep seeds are ``seed + offset``.
detailNoPayload depth: 'minimal' (~150 tokens) for sub-step calls where only the point estimate is needed; 'standard' (~1K tokens) for diagnostics + coefficient table; 'agent' (~2K tokens, default) adds violations / next_steps / suggested_functions so the LLM can plan its next call without another round-trip.agent
n_repsNoNumber of independent DGP draws per scenario. Each uses a different seed to average out Monte Carlo noise.
verboseNoPrint per-scenario progress.
verify_BNoBootstrap replications per verification run.
as_handleNoIf true, cache the fitted result on the server and return result_id + result_uri alongside the JSON payload so a subsequent tools/call can chain without re-running.
data_pathNoAbsolute path or URL to a data file. Supported: .csv / .tsv / .txt (delimited), .parquet / .pq, .feather / .arrow, .xlsx / .xls, .dta (Stata), .json / .jsonl. Schemes: file://, s3://, gs://, https://.
result_idNoOptional handle to a previously-fitted result (returned by an earlier call when as_handle=true). Tools that operate on a fitted object accept this in place of re-supplying data_path + columns.
scenariosNoSubset of {'rct', 'did', 'staggered_did', 'rd', 'iv', 'observational'}. Defaults to all six.
data_columnsNoOptional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
data_sample_nNoOptional uniform random subsample size (seed=0, deterministic) — useful on huge panels.
verify_budget_sNoWall-clock budget per verification run.

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault

No arguments

Schema Changelog

Changes observed during successful MCP inspections.

  1. First observedv0.1.0

TDQS

A3.5/5.0
Behavior3/5

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

The annotations already declare readOnlyHint=true, so the read-only safety profile is covered. The description adds a small amount of behavioral context by scoping execution to built-in DGPs rather than user data, but it does not mention simulation load, caching, or return behavior beyond what the schema hints at.

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?

One short sentence states the operation and scope with no filler or redundancy. The key phrase 'built-in DGPs with known true effects' is front-loaded, making the purpose immediately clear.

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?

Despite rich schema documentation, an output schema, and annotations, the description is too terse to fully situate the tool: it omits the distinction from verify/verify_recommendation and does not explain that scenarios in the schema are the built-in DGPs. Defaults and parameter behavior are recoverable from the schema, but intended use context is not.

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 the baseline applies and the description need not explain each parameter. The description adds no parameter-level meaning; it only names the high-level operation, while all 12 parameters are documented in the schema.

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 uses a specific verb ('Run') with a clear resource: the verify operation scoped to 'built-in DGPs with known true effects.' This distinguishes it from sibling tools like verify and verify_recommendation and conveys the ground-truth benchmarking purpose.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description gives no explicit when-to-use guidance, exclusion criteria, or direction toward verify/verify_recommendation as alternatives. The only usage clue is the phrase 'built-in DGPs with known true effects,' which implies a benchmark use case but does not state it.

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

Deploy Server

Other Tools