collect_answer

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

With no annotations, the description carries the full behavioral burden. It discloses the waiting/retry loop, the distinction between deterministic math grading and rubric-based framework/synthesis grading, and the handoff to `score`. It even explains the committed transcript and the need for human judgment, which is far beyond what the schema alone would convey.

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 front-loaded with the core purpose, then flows logically into usage, retry behavior, and grading semantics. Each sentence earns its place: no filler, no repetition, and the structure mirrors the actual invocation flow. It is appropriately concise for the complexity it covers.

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?

Given the presence of an output schema and the tool's interactive nature, the description covers all essential context: when to call it, what the return states mean, how grading differs by answer type, and what action to take afterward. This is complete enough for an agent to invoke and handle it correctly in a live interview flow.

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. The description does not add extra semantic detail about `max_wait` or `acknowledge` beyond what the schema already provides. It indirectly implies `max_wait` controls the wait via the ready:false retry loop, but it does not explicitly elaborate on parameter usage.

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 opens with a specific verb and resource: 'Listen for the candidate's spoken answer, then grade what can be graded.' It clearly distinguishes from sibling tools like `listen` (which presumably only listens) and `score` (which receives the rubric component IDs from `collect_answer`). The purpose is unmistakable and actionable.

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?

Explicitly states when to call it ('right after asking a question'), how to handle `ready: false` ('call it again'), and what not to do ('Don't fill the silence'). It also names `score` as the follow-up tool for framework/synthesis answers, giving clear when-to-use guidance relative to an alternative.

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