did_2x2

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

With readOnlyHint=true already covering the safety profile, the description goes beyond annotations by disclosing estimator mechanics, assumptions (parallel trends, no anticipation, SUTVA), and failure modes such as negative-weighted TWFE mixes in staggered designs. It also adds 'Validation: certified parity evidence' as an extra behavioral signal without contradicting the annotation.

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 text is front-loaded with the core definition and sectioned for skimmability, but it is long and contains some redundancy — the staggered-timing exclusion and the same alternatives appear in both the 'Do NOT use' block and the 'Failure modes' section. Still, nearly every clause carries diagnostic value.

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 definition covers purpose, exclusions, assumptions, preconditions, failure-mode routing, alternatives, and sample-size guidance, and an output schema exists so return values do not need to be explained in prose. For a 2x2 DID tool embedded in a large sibling family, this is complete enough for an agent to decide and invoke 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 description coverage is 100%, so the baseline is 3; the description adds meaningful method-level semantics by requiring exactly two periods, a unit-constant 0/1 treat, and by summarizing covariates, robust/cluster SE, and weights. It does not enumerate every parameter, but the schema already handles that burden.

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 specifies a precise estimator — 'Canonical 2x2 DID: two groups (treated/control) x two periods (pre/post)' — and details how the point estimate is computed via group-means differencing or OLS on the treat x post interaction. It also distinguishes itself from siblings by explicitly rejecting staggered-timing designs and naming the 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 conditions ('exactly two time periods', unit-level 0/1 treat) and explicit when-not-to-use conditions with named replacements for staggered timing, few clusters, and pre-trend failures. It also lists alternatives and a typical minimum N, leaving little to inference.

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