Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

verify_recommendation

Read-only

Verify a single recommendation against data by running statistical checks, including bootstrap and placebo tests, to produce an evidence-backed verdict with diagnostic details for confident decisions.

Instructions

Empirically verify a single recommendation.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`B`	No	Number of bootstrap replications (auto-reduced if over budget).
`rec`	Yes	A single entry from ``RecommendationResult.recommendations``.
`seed`	No	RNG seed for reproducibility.
`detail`	No	Payload 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
`budget_s`	No	Wall-clock budget per recommendation (seconds).
`as_handle`	No	If 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_path`	Yes	Absolute 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://.
`n_placebo`	No	Number of permutation placebo runs.
`result_id`	No	Optional 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.
`K_subsample`	No	Number of 50% subsample splits.
`data_columns`	No	Optional column projection. Parquet/Feather/Stata loaders honour this for fast partial reads.
`data_sample_n`	No	Optional uniform random subsample size (seed=0, deterministic) — useful on huge panels.

Output Schema

TableJSON Schema

Name	Required	Description	Default
No arguments

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.1.0Sep 15, 2026

TDQS

C2.9/5.0

Behavior2/5

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

The description adds no behavioral detail beyond what the annotations already provide. readOnlyHint=true covers the safety profile, but the description does not disclose that verification involves bootstrap resampling, permutation placebos, or budget limits (though these appear in parameter descriptions). No context about side effects, caching, or internal process is given.

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?

The description is a single, front-loaded sentence with zero waste. It states the purpose directly and efficiently. No unnecessary words or repetition. It is appropriately sized for a simple statement of purpose, even though the tool is complex.

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

Completeness2/5

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

For a tool with 12 parameters, nested objects, and an output schema, this description is insufficient. It does not explain what 'verify' entails (e.g., bootstrapping, placebo tests, robustness checks) or what the agent should expect. The parameter descriptions and output schema provide structure, but the tool-level description lacks the big picture needed to fully understand its role in a workflow.

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 coverage is 100% – every parameter has a description, including defaults and enums. The tool description itself adds no parameter information, but since the schema carries the full burden, the baseline of 3 is appropriate. The description does not need to repeat schema details.

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 states a clear verb ('verify') and a specific resource ('a single recommendation'), which is unambiguous. However, it does not differentiate from siblings like 'verify' or 'verify_benchmark' – the qualifier 'single' hints at scope but is not explicit about when this tool is preferred over those alternatives.

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?

No guidance is provided on when to use this tool versus alternatives. There is no mention of prerequisites, expected inputs (beyond schema), or conditions that would make it the right choice. The description gives no exclusions or comparisons to sibling tools.

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

Deploy Server