导入卖家报表

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

Annotations already establish that this is a non-read-only, non-idempotent write, so the description only needs to add context beyond them. It does add one meaningful behavioral guarantee — 不会连接或写入外部平台, meaning the side effects are purely local. However, it says nothing about re-import behavior, validation, or failure modes, so disclosure beyond the annotations is minimal; there is no contradiction with the annotations.

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 short sentences with zero filler: the primary action is front-loaded and the scoping statement about not touching external platforms follows directly. No schema contents are restated and every sentence earns its place.

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 7 parameters, 4 required, and no schema descriptions or output schema, two sentences are insufficient. The description omits what 'standardized' means, the expected shape of rows, how the period/currency fields behave, and what occurs after a successful save, leaving a non-idempotent write operation under-specified 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 0%, so the description carries the full burden of explaining the 7 parameters, and it does not. The phrase 标准化 JSON 报表 offers only a weak hint that rows holds the JSON payload, but none of project_id, platform, report_type, currency, period_start, or period_end is given any meaning beyond the bare schema fields. This fails to compensate for the absent schema descriptions.

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 states a specific verb (保存/save), a resource (seller-authorized standardized JSON report), and the destination (本地/local), so the agent knows exactly what the tool does. The follow-up 不会连接或写入外部平台 clarifies that it is local-only and differentiates it from any external-sync behavior. It stops short of the top tier because it never explicitly contrasts with a sibling tool such as evidence_export or report_list.

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 use case is implied: invoke when a seller-authorized standardized JSON report needs to be persisted locally, as indicated by 把卖家授权的标准化 JSON 报表保存到本地. No explicit when-not-to-use conditions, prerequisites, or alternatives are named, so an agent must infer the selection criteria from the verb and context alone.

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