qdid

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 restate read-only. It goes well beyond by disclosing assumptions (CIC rank invariance, continuous support, SUTVA), pre-conditions, and failure modes. It also names the validation ('certified parity evidence') and gives typical minimum N. This is rich behavioral context beyond the structured annotations.

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 long but every sentence earns its place. It front-loads the core definition and formula, then moves to critical differentiators (CiC), assumptions, pre-conditions, failure modes, and alternatives. No filler or repetition; it's structured as a decision aid. The length is justified by the method's complexity and the need to avoid misuse.

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 covers purpose, usage context, assumptions, pre-conditions, failure modes, alternatives, and sample-size guidance. It even mentions validation. Given that an output schema exists (context signals show it), the return format doesn't need to be described. The description is complete for an agent 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 coverage is 100%, so all 12 parameters are already documented. The description adds extra semantics by linking n_boot to a failure-mode remedy (raise to 2000) and quantiles to a restriction suggestion ([0.2, 0.8] for thin tails). It also explains the 'detail' parameter's purpose in agent planning. These additions go beyond the schema, so a 4 is appropriate.

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: 'Quantile Difference-in-Differences (QDiD): applies the DiD contrast to quantiles, [Q11(t)-Q10(t)] - [Q01(t)-Q00(t)]'. It names the method, gives the exact formula, and immediately distinguishes it from changes-in-changes, explicitly naming the sibling sp.cic. This is a specific verb-resource combination that an agent can unambiguously select.

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?

Usage guidance is explicit: it states the design (2x2), the pre-conditions (panel or repeated cross-section, binary group and time), and exactly when NOT to use it ('NOT changes-in-changes'). It provides specific alternatives (sp.qte, sp.did, sp.rifreg) and failure modes with concrete remedies, e.g., raising n_boot to 2000. An agent knows exactly when to call this tool vs. alternatives.

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