boss_watch_run

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

No annotations are supplied, so the description carries the full behavioral burden, and it does disclose that only newly added jobs are returned – implying persistent state across runs. It does not say whether the call triggers a live crawl, how long it takes, whether returned jobs are marked as consumed, or whether repeated invocations are idempotent. For an execution tool with side effects and no annotations, that is a substantial gap.

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 action and the return value are front-loaded in one compact clause, and the availability constraint is clearly bracketed as metadata. Nothing is redundant, though the extreme terseness leaves the behavioral gaps noted above rather than fixing them.

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?

With no annotations, no output schema, and a single-parameter mutation-style execution tool, the description should say more about the runtime behavior and the shape of the returned job list. It conveys the core contract (run a watch, get new jobs) and the eligibility gate, which is the minimum viable set, but not enough for an agent to predict cost, latency, or state effects.

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?

There is a single required parameter whose schema description ('监控名称') already covers it at 100% coverage, so the baseline of 3 applies. The description adds nothing about name format, case sensitivity, or where valid names come from (presumably boss_watch_list).

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 names a specific action and result in '执行指定监控并返回新增职位列表' – run a named watch and get back only newly found jobs. This separates it from boss_watch_list (list watches) and boss_watch_add/remove (manage them), which are the nearest siblings. It stops short of naming those siblings explicitly, so it is clear but not fully differentiated.

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 bracketed availability block (roles=candidate; candidate_platforms=zhipin; recruiter_platforms=-) tells the agent who may call it and implicitly who may not, which is genuine conditional guidance. However, it never states prerequisites such as needing an existing watch name from boss_watch_list, nor does it point to alternatives when the role or platform does not match.

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