bcf_factor_exposure

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

Annotations declare readOnlyHint=true and openWorldHint=false. The description goes well beyond these by disclosing failure modes (MCMC diagnostics failing, prior sensitivity), validation tiers, internal propensity model fitting, and diagnostics recommendations. It also mentions the compression via SVD or loadings, which is a behavioral detail not in annotations. No contradiction with annotations.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

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

The description is well-structured with labeled sections (Validation, Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). It is concise for the complexity, each sentence adds value, and the core purpose is front-loaded. No wasted words.

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

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

The description covers purpose, validation, assumptions, pre-conditions, failure modes, alternatives, and typical sample size. Given the tool's complexity (14 parameters) and that an output schema exists, this is complete for an agent to decide when to call and what to expect. It does not explain return values, but the output schema covers that.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all parameters have descriptions. The tool description adds minor context: it mentions 'user-supplied loadings' and 'SVD' which clarifies the 'loadings' parameter, and 'PCA-factor scores' clarifies 'n_factors'. However, it does not deeply elaborate on each parameter beyond what the schema provides, so the baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: it applies BCF to PCA-factor scores of a high-dimensional exposure vector, using SVD or user-supplied loadings, then fits one BCF per factor. This distinguishes it from siblings like bcf, bcf_longitudinal, and bcf_ordinal, which likely handle different structures. The verb 'fits' and resource 'BCF' are specific.

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

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

The description provides pre-conditions (covariates, treatment, outcome), assumptions (unconfoundedness, overlap), and typical minimum N. It lists alternatives (sp.dml, sp.auto_cate, sp.causal_forest) but does not explicitly contrast with the bcf family (e.g., when to use bcf vs bcf_factor_exposure). This is a minor gap but the intended use case is implied by the title.

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