ddd

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

Annotations declare readOnlyHint=true, so the agent knows this is a read-only estimation operation. The description adds substantial behavioral context beyond that: it discloses the weaker parallel-trends assumption, the no-anticipation and SUTVA assumptions, the negative-weights failure mode under staggered adoption, and the roadmap for a heterogeneity-robust variant. It also gives a typical minimum N of 100. The only minor gap is not describing the return payload structure, but the output schema exists and the detail parameter documents payload depths.

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 dense but well-organized: definition, validation, assumptions, pre-conditions, failure modes, alternatives, and minimum N. Every sentence carries information. It is longer than typical but justified by the methodological complexity of DDD. The structure is logical, moving from what it is to when to use it to when not to use it.

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 causal-inference estimator with 15 parameters and a rich output schema, the description covers all critical decision points: identification assumptions, pre-conditions, failure modes, alternatives, and sample size guidance. The output schema and detail parameter handle return-value documentation. Nothing an agent needs to decide whether to call this tool and how to interpret its results 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 description coverage is 100%, so the baseline is 3. The description does not add parameter-level detail beyond the schema, but it does contextualize the key parameter 'subgroup' by explaining its role in the DDD design ('within-treatment-group subgroup that is unaffected by treatment'). The pre-conditions also clarify what values subgroup must take. This is adequate given full schema coverage.

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 opens with a precise definition: 'Triple Differences (DDD) estimator' and immediately explains the methodological mechanism ('Adds a within-treatment-group subgroup that is unaffected by treatment as an additional control dimension'). This clearly distinguishes it from DID estimators and other causal inference tools. The verb 'estimates' is implicit but the resource and scope are unambiguous.

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 guidance: it relaxes parallel trends from 'same trend across groups' to 'same differential trend across subgroups within groups'. It lists pre-conditions (treat x time x subgroup variation exists; subgroup is binary and meaningful), failure modes (staggered adoption with heterogeneous effects), and names alternatives (sp.did_2x2, sp.callaway_santanna). This is exemplary routing guidance.

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