did_design_contract

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

The description goes beyond the readOnlyHint by explaining the tool's epistemic limits: it reports what the result object records and 'cannot verify that a recorded assumption is true of the data.' It also documents the failure mode ('Result carries no model_info -> Every step is reported undetermined'), which is genuinely useful behavioral disclosure.

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 compact and well-structured, using labeled sections (Assumptions, Pre-conditions, Failure modes, Alternatives) to pack substantial context without rambling. Every sentence serves a distinct purpose, and the main scoping statement is front-loaded.

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 description provides essential usage context—pre-conditions, failure modes, and alternatives—and the existence of an output schema means return-value details are handled elsewhere. It doesn't clarify whether data_path can substitute for `result`, but the schema descriptions cover the input options; overall it's complete for an agent to decide whether to call it.

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?

All 7 parameters already have schema descriptions (100% coverage), so the description adds no new parameter-specific semantics. The description's pre-condition loosely aligns with the `result` parameter but doesn't elaborate on `detail`, `as_handle`, or `data_path`. Baseline 3 is appropriate because 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 uses a specific verb ('Report') with a precise resource ('which of Baker, Callaway, Cunningham, Goodman-Bacon & Sant'Anna's (2026) eight forward-engineering steps a fitted DiD result actually pins down') and enumerates the steps (target parameter, identifying assumption, estimation strategy, etc.). It distinguishes itself from siblings by explicitly naming alternatives later in the description.

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 states a clear pre-condition ('a fitted DiD result object') and lists explicit alternatives ('sp.audit_result, sp.assumption_audit, sp.cs_report'), which routes an agent away from this tool when those are more appropriate. It does not, however, spell out the exact selection criteria between this tool and each alternative, so it falls just short of full guidance.

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