gardner_did

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

Annotations already declare readOnlyHint=true, and the description does not contradict that. Beyond the annotations, it discloses the internal procedure (residualization, two-stage estimation), the validation status ('certified parity evidence'), and important model assumptions that affect result interpretation. This adds meaningful context not available from annotations alone, though it does not discuss side effects like caching or resource usage.

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 well-structured into sections (Assumptions, Pre-conditions, Failure modes, Alternatives) and packs substantial information, but it is long and ends abruptly mid-sentence ('Typical minimum...'), which suggests incomplete drafting. While the density is justifiable for a complex estimator, the truncation hurts readability and compactness.

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 econometric tool with an output schema, the description covers method, use cases, assumptions, failure modes, and alternatives comprehensively. The only notable gap is the truncated final sentence and a lack of mention of parameter interactions (e.g., event_study vs ATT), but those are already defined in the input schema. Overall, an agent has enough context to call this 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 description coverage is 100%, so parameters are fully documented elsewhere. The description adds pre-condition context (e.g., panel structure, never-treated group) that indirectly informs parameter choice, but it does not directly elaborate on any specific parameter beyond the schema. This matches the baseline for high schema coverage with modest descriptive additions.

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 clearly identifies the estimator ('Gardner (2021) two-stage DID'), explains the two stages, and differentiates it from siblings by noting it is 'numerically close to Borusyak-Jaravel-Spiess imputation' and listing explicit alternatives. An agent can understand exactly what this tool computes and how it differs from related estimators.

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 pre-conditions, failure modes, and actionable alternatives. It tells the agent when to use this tool (e.g., for heterogeneous treatment effects) and when to switch (e.g., pre-trend violation -> honest_did; negative weights -> heterogeneity-robust estimators). It names specific sibling tools as alternatives, leaving no ambiguity about selection.

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