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

The description claims '重导幂等' (re-import is idempotent), which directly clashes with the annotation idempotentHint=false. Per the rubric an explicit contradiction with structured annotations caps this dimension at 1. Without the conflict, the dedup/no-overwrite/500-row context would have scored highly.

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-loads the login requirement and core function, then packs workflow, dedup rule, limits and return shape into dense clauses. Nearly every sentence earns its place, though the run-on style makes it slightly heavy to parse.

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?

Despite no output schema, it discloses the return surface (只返回计数; skipped 仅行号和去敏预览) and mutation semantics (仅补空、不覆盖手填). For a mutation tool it is largely complete, missing only explicit permission/auth detail beyond '需登录'.

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 only parameter is 'text' with 0% schema description coverage, and the description never names it or explains what content it must hold beyond the generic '导入...粘表'. With a single undocumented parameter the description was expected to compensate and does not.

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 — import/paste a CSV/TSV/Excel table into broker leads — plus concrete scope limits (无表头 supported, unknown columns to remarks, max 500 rows). An agent can distinguish it from list_broker_leads and scan_broker_matches without opening any 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?

Explicitly places the tool in a pipeline: 先整理 OCR/聊天/表格 → 本工具 → 念 headerMap 请用户确认 → list_broker_leads 核对 → scan_broker_matches, naming the upstream prep and the downstream siblings by name. It also states a hard precondition (【需要登录】) and an outcome limit (无手机号的线索无法归因未来注册).

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