athena_interaction_credit

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

With no annotations, the description provides a notable behavioral caveat: missing 2x2 cells remain UNIDENTIFIED. However, it does not state whether the tool mutates inputs or what side effects occur, leaving the no-annotation burden only partially met.

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, zero filler; first sentence front-loads the verb and object, second adds a critical caveat.

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?

Without an output schema or annotations, the description should explain the expected structure of 'experiments', the purpose of 'analysis_key', and the output format of the contrasts. It does not cover these, though the unidentified-cells warning is useful.

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 descriptions cover none of the three parameters. The description only loosely connects 'experiments' to intervention/outcome observations, and leaves 'analysis_key' and 'actor' undefined, so the agent lacks needed parameter semantics.

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 identifies the tool's function: estimating main and pairwise interaction contrasts. The phrase 'from supplied intervention/outcome observations' defines the input context, and the name 'interaction_credit' distinguishes it from credit assignment/summary siblings.

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 concrete usage context ('supplied intervention/outcome observations') and the statistical goal, so an agent can infer when to select it. It does not explicitly name alternative tools or state when not to use it.

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