did_bcf

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

Annotations mark this as read-only, and the description complements that by explaining what the tool estimates, what assumptions it relies on, and what failure modes may invalidate it. It adds practical behavioral context beyond the annotations without contradicting them.

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 long but well-structured with clear labeled sections for assumptions, pre-conditions, failure modes, and alternatives. Most sentences carry substantive guidance; only the trailing alternative list is somewhat redundant with the sibling tool list.

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?

For a complex DiD estimator with 14 parameters, an output schema, and strong assumptions, the description is comprehensive. It covers model mechanics, data requirements, validity conditions, common failure modes, and fallback methods, so an agent has what it needs to invoke the tool correctly.

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 coverage is 100%, so the schema already documents all parameters. The description adds useful semantic guidance on key inputs, for example that treat is 'binary (0/1) for 2x2, or first-treatment-period (int) for staggered' and that at least one pre-treatment period is required, which goes beyond the schema's terse descriptions.

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 uses a specific verb ('Fits') and a specific resource ('a BART-style ensemble with treatment and prognostic terms on the DiD residuals') and states the output ('heterogeneous treatment-effect posterior draws per unit'). It clearly differentiates did_bcf from sibling BCF tools by emphasizing the DiD residual construction, and it names alternatives.

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 gives explicit when-to-use context via assumptions, pre-conditions, and failure-mode triggers, such as 'Pre-trend joint test p < 0.05 -> Use sp.sensitivity_rr...' and 'Staggered treatment timing with TWFE method -> use Callaway-Sant'Anna, Sun-Abraham, or BJS imputation.' It also names concrete alternative tools, so an agent can route correctly.

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