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

Annotations already declare a safe read-only, non-destructive operation, but the description adds substantial context: the loop terminates on ready_to_submit, no estimate or price is produced (with the compliance phrasing to use), and there is an explicit do-not-collect list (SSN, FEIN/EIN, DOB, licence number). It also instructs to ask `ask` verbatim with its options and wait — real behavioral guidance beyond 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?

The scope/loop and the submit hand-off are front-loaded, and every paragraph carries distinct information (flow, customer-type routing, no-pricing stance, prohibited fields). However, some sentences are grammatically tangled and dense ('sending back the collected it returns each time'), which slightly hurts scannability.

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?

Output schema exists so return values need not be explained, and the description still covers the loop termination condition, the personal-vs-commercial routing decision, the hand-off tool, and the compliance/data-collection boundaries. For a stateful, multi-step intake tool this is complete enough to call correctly.

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, but the description adds the round-trip protocol — send back the returned `collected` on every call after the first and pass each turn's answer under answer_as.key — plus the warning that this `collected` is not the quote flow's. That meaningfully clarifies how the 3 parameters are threaded across calls.

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 opening line states exactly what the tool returns — the next commercial auto intake question — and frames it as 'step 1 of 2' of a named flow. It explicitly contrasts the resource with personal auto (route_to_personal / next_question) and with submit_commercial_application, so an agent can place it among siblings without opening a schema.

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?

Gives concrete when-to-use rules: call repeatedly until ready_to_submit is true, echoing `collected` and each answer under answer_as.key, then hand off to submit_commercial_application. It also names the alternative path explicitly (personal-auto drivers route to next_question) and says 'When it is not clear which kind of customer this is, start here.'

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