汇总统计

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

With no annotations, the description carries the full behavioral burden. It discloses what is read (local library/tasks/registrations, an environment self-check, optionally the Tomato backend), which is meaningful. It omits whether the backend read requires an authenticated session (login_tomato / set_tomato_cookies exist as siblings), and gives no side-effect or rate-limit context, leaving a notable gap for a network-touching 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?

A single dense sentence with the environment/aggregation scope front-loaded and the conditional remote clause at the end. No filler, though the semicolon-linked clauses compress two distinct behaviors into one line.

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?

There is no output schema and no annotations, so the description must carry the load. It names the data sources but not what the returned statistics contain or how the self-check result is presented, which is a gap for a multi-source aggregate tool. Adequate but not complete.

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 both remote and headless are already documented in the schema. The description reinforces that remote=true triggers an extra backend read, but adds no syntax or format detail beyond the schema, and never mentions headless. Baseline 3 is correct.

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?

States a specific aggregate verb and enumerates the resources it summarizes: 本地文稿库/任务/登记 plus 环境自检, and the additional backend read when remote=true. An agent can tell it is a roll-up/stats tool rather than a list or create tool. It stops short of explicitly naming a sibling it replaces, so it falls just below 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?

It gives one conditional: remote=true additionally reads the 番茄 backend lists, implying the default local-only mode. However there is no explicit when-to-use-vs-alternatives guidance against siblings like get_publish_status or list_novels_tomato, so usage is only implied.

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