boss_watch_add

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

No annotations are supplied, so the description carries the full burden of behavioral disclosure. It does not say whether saving is idempotent, what happens when a watch with the same name already exists, whether the monitor starts running immediately, or how to schedule it. For a create-type tool with zero annotation coverage, this is a real 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?

It is a single front-loaded clause with no filler, and the availability constraint is appended compactly. The bracketed availability tag is somewhat cryptic in phrasing, but it does not waste space.

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 mutation that persists configuration, has four parameters, no output schema, and no annotations, so the description should explain persistence and duplicate semantics as well as what a successful save returns. It supplies only the purpose and a platform/role gate, which is too thin for a tool of this type.

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 every parameter (city, name, query, salary) is already documented inline. The description only adds that these values collectively form the saved 'search criteria', which is a marginal addition, so the baseline of 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 states a specific verb and resource: saving search criteria for incremental monitoring ("保存增量监控的搜索条件"). This clearly distinguishes it from boss_watch_list, boss_watch_run, and boss_watch_remove. However, it does not explicitly contrast itself with boss_preset_add, which is a similar 'save a config' sibling, so it falls short of a 5.

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 phrase "增量监控" implies the use case: persist a search so it can be re-run incrementally later. The availability tag also restricts it to the candidate role on the zhipin platform. Still, the description never states when to use this instead of boss_preset_add, or when-not to use it, leaving usage to inference.

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