mediate_interventional

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

Annotations already mark this read-only, and the description is consistent ('Identifies'). Beyond that, it discloses validation tier, assumptions (sequential exchangeability, positivity, correct model specification), pre-conditions, failure modes with concrete remedies, and a typical minimum N. This is rich behavioral context that annotations do not provide.

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?

Every sentence serves a distinct purpose: purpose, validation, assumptions, pre-conditions, failure modes, alternatives, and minimum N. Section labels make it scannable despite the length, and the core purpose 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?

For a complex causal inference tool, the description covers identification conditions, assumptions, required inputs, failure modes, and remediation, with alternatives. An output schema exists, so not describing return values is acceptable. Nothing essential to correct invocation or expectation-setting 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?

Input schema descriptions cover 100% of the 11 parameters, so the baseline is 3. The description adds conceptual context (e.g., covariates and tv_confounders as sequentially measured variables) but does not elaborate on individual parameter syntax, defaults, or formats beyond what the schema already states.

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 specific statistical target ('Interventional (in)direct effects'), then states the verb 'Identifies mediation effects' and the precise condition (presence of treatment-induced mediator-outcome confounders where natural effects are not identified). This distinguishes it from siblings like mediation, frontdoor, or mediation_decompose without needing the schema.

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 gives a clear use case ('where natural (in)direct effects are not identified') and lists explicit alternatives (sp.tmle, sp.g_computation, sp.ipw). It also lists pre-conditions and typical N. However, it does not provide explicit 'when-not-to-use' conditions or decision rules for choosing between the alternatives, so it is not a full routing guide.

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