start_interview

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

Annotations only declare non-read-only, non-destructive, non-open-world; the description adds real behavioral context beyond that, notably that with MCP elicitation support the answers are saved immediately as a side effect, plus the type-coercion of free-text answers. This surfaces a side effect the annotations alone would hide.

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?

Mostly efficient and front-loaded, with the interview-flow explanation preceding the Args block. It is somewhat dense and has a mid-sentence line break, but each clause carries useful information rather than repetition.

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?

An output schema exists, so return-value documentation is unnecessary, yet the description still describes the returned question shape (`confirm` flag) and the answer format. Combined with the alternative-routing notes, an agent has enough to call and chain this tool 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 coverage is 0%, so the description carries the full burden and does compensate: it defines `path` (folder holding steamworks.yaml), `gate` (0-3), `max_questions` (1-5, default 3), and `use_form`. It adds range constraints and purpose beyond the bare schema types, though it could be slightly more explicit about defaults.

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 explains that this returns the next batch of interview questions with suggested answers, and that `confirm: true` marks a value already found (e.g. by the scan) needing only confirmation. It distinguishes itself from siblings by routing store-text questions to `generate` and answer-saving to `set_field`. The opening fragment 'Next questions for the user' lacks a strong verb, but the purpose is recoverable.

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 states the workflow (ask in chat, then persist via set_field) and names explicit alternatives/exclusions: store texts go to `generate`, and `use_form=false` disables the form path. It does not cover when to begin an interview versus other flows, but the routing guidance is clear.

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