boss_stats

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

With no annotations, the description carries the safety burden. It explicitly says 只读聚合 (read-only aggregation), so an agent knows there are no side effects, and it lists the data sources aggregated. It stops short of describing output shape, but that is a minor omission for a read-only stats tool.

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 core purpose and availability are stated in a compact, front-loaded way. The duplicated '可用性:' prefix is a small formatting flaw, but the description has no wasted sentences.

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?

This is a low-complexity tool: one optional parameter, no nested objects, no output schema, and no annotations. The description covers the read-only nature, data sources, and role/platform applicability, which is sufficient for an agent to invoke it correctly with sensible defaults.

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%, and the only parameter, days, is already documented as the statistics window. The description adds no extra meaning to the parameter, so it stays at the baseline.

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 identifies a specific resource (投递转化漏斗/application-conversion funnel) and a clear operation (read-only aggregation/统计) with the data domains it covers. That is enough to distinguish it from sibling stats tools like boss_agent_stats.

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 availability clause explicitly scopes usage to candidate role on zhilian and zhipin and marks recruiter platforms as not applicable, giving a concrete when/where condition. It does not name an alternative sibling, but for a single metrics endpoint the role/platform constraint is useful guidance.

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