Causal Decision Agent

Overview Schema Source Related Servers Discussions Admin

poisson

Read-only

Fit Poisson regression to count data, producing coefficients or incidence rate ratios with confidence intervals, robust standard errors, and validation for evidence-backed decisions.

Instructions

Poisson regression via MLE (IRLS). Validation: certified parity evidence.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`x`	No	Independent variable names (alternative to formula).
`y`	No	Dependent variable name (alternative to formula).
`irr`	No	If True, report Incidence Rate Ratios (exp(beta)) instead of raw coefficients.
`tol`	No	Convergence tolerance.
`alpha`	No	Significance level for confidence intervals.
`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
`offset`	No	Offset variable (log of exposure already computed).
`robust`	No	Standard error type: "nonrobust", "robust"/"hc0", "hc1".	nonrobust
`cluster`	No	Variable name for clustered standard errors.
`formula`	No	Model formula, e.g. "y ~ x1 + x2".
`maxiter`	No	Maximum IRLS iterations.
`weights`	No	Frequency/analytic weight variable.
`exposure`	No	Exposure variable (will be logged and used as offset).
`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`	No	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://.
`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.
`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

B3.2/5.0

Behavior2/5

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

The annotation readOnlyHint=true is present, which covers safety, but the description adds little behavioral context. The phrase 'Validation: certified parity evidence' is cryptically worded; it may refer to an implementation verification but does not disclose what the tool returns, whether it supports chaining, or any side effects. No contradiction with annotations is present, but the description fails to provide meaningful behavioral transparency beyond the purpose statement.

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 exceptionally concise: two short sentences with zero filler. The main purpose is front-loaded, and the validation note is clearly separated. Every part earns its place, and the text is appropriately sized for the information it conveys.

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?

Given the tool's complexity (18 parameters, 100+ sibling tools) and the sparsity of the description, the agent lacks essential context for correct use. There is no guidance on when to reach for poisson over similar tools, no mention of typical workflow steps, and the ambiguous 'validation' statement does not help. While the schema covers parameter details naturally, the description fails to place the tool in the broader analytical context.

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 is 3. The description itself does not add any parameter-level meaning, but the schema already thoroughly documents each of the 18 parameters, including defaults, enums, and format expectations. No value is missing from the description, but it also does not augment what the schema provides.

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 clearly states 'Poisson regression via MLE (IRLS)', identifying the specific statistical model, estimation method, and algorithm. This distinguishes it from sibling tools like nbreg, fepois, or glm. The Verb+resource structure is explicit and unambiguous.

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. Sibling tools include many count-data models (nbreg, xtnbreg, fepois, zip_model, zinb), but the description gives no criteria for selecting poisson over these or when a different model would be more appropriate. There is no mention of prerequisites, data requirements, or exclusions.

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

Deploy Server