fde_interview

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It discloses important side effects: idempotent overwrite/merge by nodeId, automatic recomputation of the enterprise portrait, and non-persistence when prompts_only=true. It does not cover auth, rate limits, error behavior, or the normal-mode return payload, but the core mutation behavior is transparent.

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 one dense sentence that front-loads the main purpose and then packs in modes and side effects with no filler. It is efficient, though the heavy use of domain shorthand like '五要素' and '三问' may require prior familiarity with the guide.

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 no output schema and no annotations, the description covers persistence, idempotent merging, profile recalculation, and the prompts_only branch. However, it does not state what a successful normal-mode call returns, what preconditions apply (e.g., enterprise_id must already exist), or how this tool fits with the many sibling FDE tools. These gaps leave moderate uncertainty for an agent.

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 maps the five elements and three questions to the schema's nested objects and adds that prompts_only returns six scripts, but most parameter meaning is already present in the input schema. The added value is modest because the schema already describes the idempotent node_id key and the prompts_only no-persistence behavior.

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 statement—'FDE 访谈结构化落盘'—and explains the core behavior: node-wise five-element collection, idempotent merge by nodeId, and automatic enterprise profile recalculation. It also distinguishes the prompts_only mode clearly. However, it does not explicitly differentiate the tool from sibling tools such as fde_compose or fde_classify, so the distinction is implied rather than 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?

The description gives clear usage context: normal mode persists interview nodes, while prompts_only=true returns pre-interview follow-up scripts and skips persistence. It also explains multi-round append behavior as idempotent by nodeId, which tells the agent it can safely call repeatedly. It stops short of naming alternative tools or stating when not to use this tool, so it is not a 5.

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