network_exposure

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

The description goes far beyond the readOnlyHint annotation. It details validation tiers, known limitations (complete design not implemented), assumptions (correct exposure mapping, positivity, fixed adjacency), pre-conditions (binary matrix, same lengths, known design), and failure modes (low exposure cell counts, conservative variance). This gives an agent a rich understanding of the tool's behavior and edge cases.

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 well-structured with labeled sections (Validation, Known limitations, Assumptions, Pre-conditions, Failure modes). Each sentence adds substantive information for a complex estimator. It is front-loaded with the core purpose and then provides necessary details. It earns its length, though it could be tightened slightly.

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 tool with 13 parameters and complex statistical assumptions, the description covers essential context: estimator type, assumptions, pre-conditions, limitations, and failure modes. It does not describe return values, but an output schema exists, so that is not a gap. It is reasonably complete for an agent to decide whether and how to call it.

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 all parameters are documented in the schema. The description adds some context about p_treat and design (e.g., approximation conditions), but it does not provide additional semantics for each parameter beyond what the schema already states. The description adds marginal value over the schema, so a baseline 3 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 clearly states the tool computes an Aronow-Samii Horvitz-Thompson estimator for arbitrary interference with a user-supplied exposure mapping. It names a specific estimator and method, so the purpose is unambiguous. However, it does not explicitly contrast with sibling tools like 'spillover' or 'interference', so it doesn't fully distinguish from alternatives.

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 provides some usage conditions: it warns that design='complete' is not implemented and raises NotImplementedError, and it advises using design='bernoulli' only if the assignment mechanism matches. It also gives failure-mode guidance (switch to coarser mapping or increase sample size). But it never explicitly says when to choose this tool over siblings or names alternatives, leaving the selection logic implicit.

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