pretrends_test

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

The description discloses the test's statistical behavior and limitations (low power problem, Roth 2022), assumptions (joint test vs zero), and that 'failing to reject is consistent with parallel trends but does NOT prove it.' It also adds practical details like typical minimum N and recommended cluster-robust SE. These go well beyond the readOnlyHint annotation, which only indicates the operation is safe to run.

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 longer than average but tightly packed with essential information, organized into clear sections (purpose, assumptions, pre-conditions, failure modes, alternatives). Every sentence earns its place; no fluff. It could arguably be trimmed slightly, but the density and structure justify the length for a statistically nuanced tool.

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?

Given the tool's complexity mis - a joint pretrends test in DiD - the description covers purpose, usage conditions, assumptions, limitations, failure modes, alternatives, and even practical recommendations (pairing with sp.honest_did, typical minimum N). An output schema exists, so return values need not be described. Nothing an agent needs to correctly invoke this tool is missing.

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 baseline is 3. The description adds meaning to the 'result' parameter by specifying pre-conditions: it must contain at least one pre-treatment period coefficient and the covariance between pre-period coefficients. It also recommends cluster-robust SE, directly relevant to the result object. This contextualizes parameters beyond their schema definitions.

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 states a specific verb and resource: 'Joint Wald test of pre-treatment ATTs (or event-study leads) against zero' and names it 'the canonical sanity check for the parallel-trends assumption in DiD designs.' It clearly distinguishes itself from related tools by naming alternatives like sp.honest_did, sp.sensitivity_rr, and sp.event_study.

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 explicit when-to-use and when-not-to-use guidance: it specifies pre-conditions (at least one pre-treatment period coefficient, covariance available), failure modes (single pre-period, low power), and directly names alternatives with conditions for switching ('High-power study rejects but visual pretrends look flat -> Use sp.honest_did + sp.sensitivity_rr'). It also advises pairing with other tools as standard practice.

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