rdit

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

Annotations only declare readOnlyHint, so safety is already covered; the description adds value by documenting failure modes (density jumps at cutoff -> rdplotdensity; bandwidth sensitivity -> MSE-optimal bandwidth) and typical minimum N. This tells the agent how the estimator behaves and what diagnostics matter, though it does not spell out the exact output payload.

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?

Dense but purposeful: assumptions, pre-conditions, failure modes, alternatives, and minimum N each add selection/reasoning value. No markdown structure, but the sentences are front-loaded with the method name and are not redundant with the schema.

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 with 16 params and an output schema, the description covers statistical assumptions, preconditions, common failure modes, alternative tools, and minimum sample size. It does not need to describe return values because an output schema is present.

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 carries parameter meaning. The description adds little parameter-specific detail; the only echo is the bandwidth-sensitivity discussion aligning with h, which does not materially extend the schema.

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 the method name 'Regression Discontinuity in Time (Hausman & Rapson, 2018)', which identifies the estimator and the design family, and it names sibling alternatives (sp.rdrobust, sp.rdrandinf, sp.rdbwselect) so an agent can disambiguate. It lacks an explicit verb like 'estimates', so it does not fully meet the 5-level bar.

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?

Provides explicit pre-conditions (continuous running variable, known cutoff, enough observations) and assumptions (continuity, no sorting, monotonicity for fuzzy designs). Lists alternatives and failure-mode remedies, but does not state explicit exclusion criteria such as 'use rdrobust for non-time running variables'.

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