boss_agent_run

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

With no annotations provided, the description carries the full burden of disclosing side effects and runtime behavior. It mentions '执行' (execution), implying real actions, but does not state what those actions are, whether they are irreversible, what systems may be affected, or what thresholds control. The dry_run parameter exists in the schema but the tool description itself does not explain the safety tradeoff beyond the structured schema.

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 description is a single concise sentence and is front-loaded with the primary purpose. However, it contains a duplicated '可用性: 可用性:' typo and interleaves availability metadata that would be better placed in annotations or structured fields, slightly reducing clarity and polish.

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 complex automation tool that orchestrates scanning, decision-making, execution, and lead generation, yet there is no output schema or return-value description. The definition does not explain what the caller receives after the run completes, what 'threshold control' refers to, or how limit and dry_run affect the overall run. This leaves significant gaps for an agent deciding whether and how to invoke it.

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 two parameters are already documented with meaningful descriptions: limit controls session count, dry_run controls whether real platform actions are executed. The tool description itself does not add parameter-level detail, but per the rubric the baseline is 3 when schema coverage is high.

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 clear action ('运行一轮' — run one round) on a specific resource ('招聘自动化' — recruitment automation) and enumerates the pipeline stages: scanning, decision-making, threshold control, execution, and lead generation. It is generally distinguishable from sibling tools like boss_agent_stop and boss_agent_train, though it does not clearly differentiate itself from other 'run' siblings such as boss_watch_run.

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 provides no guidance on when to use this tool versus alternatives. It only includes availability metadata for roles and platforms, which is a constraint rather than usage guidance. There is no mention of exclusions, prerequisites, or when a caller should choose a sibling tool instead.

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