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

Annotations already convey read-only, idempotent, non-destructive behavior. The description adds value by stating deterministic behavior and specifying in detail what the single returned record contains, including conditional fields for read vs. package routes and the fallback question when information is missing. There is no contradiction with the annotations.

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?

One dense, information-packed sentence that front-loads the essential use ('Step 0') and then economically enumerates all output components without wasted prose. Every clause adds routing or output semantics.

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?

Even without an output schema, the description enumerates the record structure and all route branches (read plan for read, method family/tool fit for package, question when incomplete), which gives an agent a solid mental model of the tool's result. It does not describe score formats, error behavior, or an example, but those are secondary for a two-input router.

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?

With zero schema description coverage, the description must clarify the two parameters. It does suggest that objective is the new question and dataset_ref is the data ('which path answers it on this data'), which is meaningful, but it stops short of explaining expected formats, examples, or precise constraints. It partially compensates for the schema gap.

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 as the initial routing decision for a new question and names the exact resource it operates on: the question and the data. It goes beyond the name by enumerating the five possible route values and the conditional components of the returned record, which distinguishes it from execution-oriented siblings like answer_now or order_analytics_package.

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 opening phrase 'Step 0 for a new question' gives a clear context for when to call it: before any other path is chosen. It does not explicitly name sibling tools as alternatives or state when not to use it, so it misses the top rung, but the intended placement in the workflow is unambiguous.

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