Add follow-up questions to an open interview

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

Annotations only give readOnlyHint/openWorldHint; the description adds real behavioral context beyond them: the open form updates live, the `note` renders as a banner, everything is submitted once, the call 'Returns at once' with answers arriving through the already-waiting call, and the failure mode after submission. It does not address idempotency or whether two appends can race, and it calls the operation 'read-only'-adjacent while mutating a live form, but because that state effect is explicitly disclosed an agent is not misled.

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?

Front-loaded with purpose in the first clause, then usage, then mechanics; two tight paragraphs, no filler. Slightly dense for a definition of this length, but every sentence carries information an agent needs.

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 tool with a rich 100%-documented nested schema, no output schema, and only two hints in annotations, the description covers the remaining gaps: state effect on the live form, return timing, where answers arrive, dependency semantics, and the post-submit failure path. Nothing an agent needs in order to call it correctly is missing.

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, and the description still adds cross-field meaning the schema does not state on its own: question ids must be unique across the whole interview (not just this call) and dependsOn may name any existing question, not only earlier ones in this call. The banner behavior of `note` is also clarified.

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?

States a specific verb (append) and resource (follow-up questions to an interview that is still open) and immediately distinguishes the behavior from the obvious alternative ('instead of opening a second form'). An agent can tell it apart from ask_user_rich and await_user_answers without reading either 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 explicit triggering conditions ('after ask_user_rich returned status "awaiting"', 'while a backgrounded ask_user_rich / await_user_answers call is still waiting') and an explicit exclusion with the alternative for that case ('Fails once the user has submitted: then ask a new interview'). Both when-to-use and when-not-to-use are covered.

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