bootstrap

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

The description discloses key behaviors beyond the readOnlyHint annotation: assumptions (exchangeability, smooth functional, pivotality), pre-conditions (deterministic callable, enough resampling units), and failure modes (anti-conservative CIs with few clusters, NaN resamples). These are not inferable from the schema or annotations alone.

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 front-loaded with the core purpose ('General bootstrap inference: nonparametric, cluster, block...') followed by clearly labeled sections (Validation, Assumptions, Pre-conditions, Failure modes). Each sentence carries technical content without fluff, though the description is long and ends mid-sentence ('e...') due to truncation.

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?

An output schema exists, so return-value documentation is not required. The description covers validation tiers, assumptions, pre-conditions, and failure modes, which is thorough for a complex inference tool. The notable gap is the block-mode mismatch: the description repeatedly tells the agent to specify cluster= or block=, but the schema only offers cluster, which could confuse an agent attempting to use block.

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 baseline is 3, but the description adds meaningful semantics: it clarifies what cluster does ('resamples whole clusters') and what block would do ('preserves within-block ordering'), and defines constraints on statistic ('deterministic callable returning a finite scalar'). However, it references a 'block' mode that does not appear in the input schema, which slightly reduces the added value.

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?

States 'General bootstrap inference: nonparametric, cluster, block' with explicit CI methods (percentile/BCa/normal). This clearly identifies the tool's purpose and distinguishes it from related siblings like wild_cluster_bootstrap, especially since the failure modes section references that alternative directly.

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?

Explicitly states 'Specify cluster= or block= when data are clustered/serially dependent rather than iid' and gives failure-mode guidance: 'Few clusters yields ... -> Use a wild cluster bootstrap with Rademacher weights when the number of clusters is small (<~40)'. This tells an agent exactly when to use 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.