did_estimate

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

Annotations already declare readOnlyHint=true, so the description doesn't need to repeat safety. It adds valuable behavioral context: statistical assumptions (parallel trends, SUTVA, stability), failure modes (weighted pre-trend divergence) with a suggested remedy, and a typical minimum N of 15. This goes beyond what annotations provide and helps an agent anticipate pitfalls.

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 structured into clear labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives, Typical minimum N). Each sentence conveys distinct information, though the opening 'R-style alias' is meta and not essential. It is not overly verbose and is easy to scan.

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 complexity of synthetic DiD, the description covers assumptions, preconditions, failure modes with remediation, and alternatives. It does not explain the output format, but an output schema exists. It also does not elaborate on parameters, but the schema does. The description provides enough for an agent to decide when to use it and what to expect statistically.

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 11 parameters have descriptions in the input schema. The tool description adds no parameter-specific detail (e.g., how treat_unit or treat_time should be formatted), only general context about the estimator. Per the rubric, with full schema coverage the baseline is 3, and the description does not exceed that.

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 identifies the tool as an R-style alias for synthdid::did_estimate but never explicitly states that it estimates a synthetic difference-in-differences treatment effect. It focuses on assumptions, preconditions, and failure modes rather than a crisp verb+resource statement. The purpose is implied by the name and alias, but not directly articulated.

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 lists clear preconditions (panel with treated/control units, treatment date, pre-treatment periods) and names specific alternatives (sp.synth, sp.augsynth, sp.callaway_santanna, sp.gardner_did). It also gives a failure-mode response suggesting event-study DiD with honest bounds. This effectively tells an agent when to use the tool and what else to consider.

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