bias_factor

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

The readOnlyHint annotation already covers the safety profile, so the description does not need to belabor non-mutation. The description adds conceptual context by naming the Ding & VanderWeele bias factor, but it does not disclose behavioral details such as formula interpretation, numerical range, or how optional data/result parameters interact with the required rr_eu and rr_ud arguments.

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 very short and free of filler, which is efficient. However, for a tool with 8 parameters and a statistical concept, a single noun-phrase fragment is under-specified rather than ideally concise; it does not provide the structure an agent needs to use the tool safely.

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?

The description is incomplete relative to the tool's context: it omits usage guidance, fails to explain how the optional data_path/result_id parameters relate to the two required risk-ratio inputs, and gives no interpretive context for the returned bias factor. The output schema may cover return shape, but the surrounding call context is still too sparse.

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 the baseline is 3 even though the parameter descriptions are thin ('rr_eu parameter (float)'). The description itself adds no semantic meaning beyond the formula reference; rr_eu and rr_ud remain cryptic and are not connected to the bias-factor calculation.

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 the object as the confounding bias factor B and cites Ding & VanderWeele (2016), making the core purpose reasonably clear. However, it uses a noun phrase rather than a verb like 'computes/returns, and it does not differentiate this tool from nearby sensitivity siblings such as sensitivity_rr, evalue_rr, or sensitivity_from_result.

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?

There is no guidance on when to use this tool versus alternative sensitivity analyses, and no mention of what inputs are expected beyond the schema. The description does not explain whether rr_eu and rr_ud are risk ratios, nor does it give any exclusion or alternative-selection hints.

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