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

Annotations are absent, so the description carries the full behavioral burden — and it does substantial work: it discloses the no-charge cost behavior ('不扣费'), the row-level existence flags (decision_maker / phone_number_exists / linkedin_exists), and the underlying hunterio multi-domain-search endpoint. It stops short of covering edge behavior such as empty-result handling or rate limits, but the core cost and data-shape traits are clearly exposed.

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?

Three dense, front-loaded sentences: purpose and cost first, then the underlying endpoint, then the paid follow-up workflow. Each sentence earns its place, though the literal `monid run -p hunterio -e /multi-domain-search --query '{...}'` shell command is implementation detail of marginal value to an agent's invocation decision.

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?

An output schema exists and the input schema documents all parameters, so the description only needed to supply cost behavior, flag semantics, and the relationship to the paid sibling — all of which it provides. Minor omissions like no-result/failure behavior and rate limits keep it from a 5.

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%: all five parameters (limit, title, company, location, department) already have descriptive text with defaults and examples. The tool description adds no parameter-level meaning beyond the schema, so the baseline 3 applies.

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, resource, and cost qualifier: '免费搜索目标企业的决策者名单' (free search for a target company's decision-maker list), and explicitly positions itself against the sibling reveal_work_email by calling itself free and the reveal step paid. An agent can distinguish this tool from both siblings without opening their schemas.

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 explicit workflow routing: run this free search endpoint first, filter rows by the existence flags to find true decision makers, then call reveal_work_email() (paid) only on selected rows. This conditions tool choice on cost and sequencing, which is exactly the guidance an agent needs to chain the two siblings correctly.

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