athena_causal_robustness

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

With no annotations, the description must disclose behavioral traits itself. It adds the important caveat that this is not a formal bound, but it does not explain what the tool returns, whether it mutates state, what prerequisites exist, or what 'V8' refers to.

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 two short sentences, front-loaded with the primary purpose and ending with a valuable caveat. There is no filler or redundancy.

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?

Given no output schema, no annotations, low schema coverage, and a complex causal-inference context, the description is far too sparse. It fails to explain return behavior, parameter roles, or how to interpret the diagnostic result, leaving the agent without crucial contextual information.

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 0%, and the description only hints at the role of `adjustment` through 'leave-one-adjustment-out'. It does not explain `samples`, `treatment`, `outcome`, or `assumptions`, leaving most parameter semantics to the agent's inference.

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 identifies a specific operation: a leave-one-adjustment-out robustness diagnostic tied to a V8 linear back-door estimate. This distinguishes it from sibling tools that estimate causal effects or identify causal structure, though the term 'V8' is unexplained.

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 phrase 'around V8 linear back-door estimate' implies this diagnostic should be used after obtaining that type of estimate, and 'Not a formal hidden-confounding bound' warns against a specific misuse. However, no explicit alternatives or when-to-use instructions are provided.

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