start_story_interview

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

With no annotations, the description carries the full burden and does well: it discloses the multi-turn protocol, the verbatim-relay requirement, the termination condition ('complete'), and the side effect that the story is auto-saved. It does not say what happens to an abandoned or partially answered session, nor whether starting a second interview while one is active is allowed or destructive.

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, no filler. The return value and the session_id handoff are front-loaded before the loop instructions, which is the order an agent needs them in.

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?

There is no output schema, so the description must describe the return — it does, naming both the first question and session_id. Combined with the loop-termination and auto-save notes, an agent has everything needed to drive the interview to completion without further probing.

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 tool takes zero parameters, so there is nothing for the description to disambiguate; the baseline of 4 applies. The description correctly signals the no-argument nature implicitly by describing no inputs, only outputs and follow-up state.

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 and resource ("Begin a structured interview to capture one new career story") and immediately names what it returns, so an agent can distinguish it from save_story (direct save) and answer_story_question (continuation). The scope — exactly one story per session — is explicit.

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 clear routing: after this call, keep invoking answer_story_question with the returned session_id until status is 'complete'. What's missing is an exclusion rule — nothing tells the agent when NOT to start an interview, e.g. when the user already has a finished story to persist via save_story, or when a session is already in flight.

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