spec_curve

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

Annotations already cover the safety profile (readOnlyHint=true, openWorldHint=false), so the bar is lower. The description adds real behavioral context beyond that: the exhaustive 'runs them all' trait signals potentially heavy computation, and 'returns the sign/magnitude distribution' tells the agent what kind of result to expect. No contradiction with 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?

Two sentences, both essential: the first front-loads the action and method, the second delivers the usage condition. Zero filler words, and the methodological citation earns its place by anchoring the agent to the established technique.

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 already covered. The 12 parameters are 92% documented in the schema (including the detail enum with token counts), and the description conveys the essential scope and cost signal ('runs them all'). Nothing critical for correctly invoking the tool is missing.

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 92%, so the schema already documents the parameters well (baseline 3). The description adds marginal conceptual framing — 'model choices the user declares defensible' maps onto the controls/se_types multiverse parameters — but it doesn't clarify syntax or formats beyond the schema. It stays at baseline.

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 names a specific method (specification-curve analysis, Simonsohn et al. 2020) with a concrete verb chain: enumerates model-choice combinations, runs them all, returns the sign/magnitude distribution. This is distinct from sibling robustness/sensitivity tools because it uniquely identifies exhaustive multiverse enumeration as the core behavior.

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?

"Use when an agent needs to report robustness across a researcher-degree-of-freedom multiverse" gives an explicit, well-phrased trigger condition. It stops short of naming excluded alternatives or sibling tools one should prefer instead, so it lacks the when-not dimension that would make it a 5.

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