bartik

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

The annotations declare readOnlyHint=true, so the agent knows this is a read-only estimation operation. The description adds substantial behavioral context beyond the annotations: it discloses the asymptotic framework (many shocks, L -> inf), the minimum sample size requirement (>=50 regions), and specific failure modes with their consequences. It doesn't describe the output format in detail, but the output schema exists and covers that. The only minor gap is not explicitly stating that this is a read-only operation, but the annotation covers that.

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 and information-rich, covering assumptions, pre-conditions, failure modes, and alternatives in a compact format. It's front-loaded with the core definition. However, it's quite long and the 'Typical minimum N:...' sentence is cut off, which is a minor structural flaw. The density is justified by the complexity of the tool, but the truncation prevents a 5.

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 estimator, the description is remarkably complete: it covers the estimator's mechanism, assumptions, pre-conditions, failure modes with remedies, and alternatives. The output schema exists, so return values are documented. The only missing piece is the truncated 'Typical minimum N' sentence, but the >=50 regions condition is already stated. An agent has everything needed to decide whether to use this tool and how to interpret its results.

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 schema already documents all 11 parameters. The description adds context for the key parameters (shares, shocks, endog, y) by explaining the econometric mechanism, but doesn't add syntax or format details beyond what the schema provides. Baseline 3 is appropriate when the schema does the heavy lifting.

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 tool as a Bartik/shift-share IV estimator, names the specific econometric references (Adao-Kolesar-Morales 2019; Borusyak-Hull-Jaravel 2022), and explains the core mechanism: pre-period shares x exogenous shocks as an instrument for local outcome exposure. This is a specific verb+resource combination that distinguishes it from the many sibling tools.

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 extensive usage guidance: explicit assumptions (exogeneity of shocks, shock-level IV, many shocks asymptotic framework), pre-conditions (pre-determined shares, as-good-as-random shocks, >=50 regions), and failure modes with specific remedies (Herfindahl concentration -> use sp.shift_share_se; weak first stage -> sp.anderson_rubin_ci; pre-trend correlation -> drop shock or add controls). It also names alternatives (sp.iv, sp.shift_share_se, sp.shift_share_political, sp.shift_share_political_panel). This is exemplary.

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