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

Annotations already declare readOnlyHint, destructiveHint false and closed-world, so the safety profile is covered structurally. The description adds a real behavioral constraint not present in annotations: this tool must not be used to gather sensitive identifiers or account data, which shapes how an agent should handle the conversation. It does not describe the shape or size of what comes back, which is the main remaining gap.

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, front-loaded with the trigger condition, no preamble or filler. The second sentence carries a long enumeration, but each listed item is a distinct sensitive data category that earns its place in a privacy-relevant guardrail.

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?

For a zero-required-parameter, read-only tool with full schema coverage there is little to document, and the safety constraint is well covered. However, with no output schema, the description never tells the agent what it receives back — a list of questions, a grouped checklist, a template — leaving the return value entirely unspecified.

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?

The single parameter has 100% schema description coverage and an enum, and the description's 'installer, a lender, or both' merely restates the enum values already documented. The schema and description both note the 'both' default, but the description adds no new meaning about how the audience changes the returned questions.

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 says when to reach for the tool ('preparing questions for an installer, a lender, or both') and implies it produces a set of questions, but never states the verb or the resource explicitly — an agent has to infer that it returns a checklist of questions to ask rather than, say, a decision tree or a document template. It is distinguishable from the explain_* siblings only by inference, since none are named.

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?

It gives an explicit use case plus a hard exclusion ('Do not use this to collect the answers, a TFN, an SSN...'), which is genuinely useful routing guidance. It stops short of naming an alternative sibling for the excluded cases, so the agent is told what not to do but not where to go instead.

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