get_capabilities

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

Annotations already declare readOnlyHint, idempotentHint, non-destructive and closed-world, so the safety profile is covered. The description still adds a genuine behavioral fact not present in structured fields: this call needs no browser launch, which tells the agent it is a side-effect-free metadata probe. It stops short of describing rate limits or what is actually returned.

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 short sentence plus one clause, no filler, and the low-cost nature ("no browser needed") is placed last as a qualifier. It is efficient, though the front half is dense and could be more explicit about what is being enumerated.

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 parameters, no output schema, and annotations covering safety, the description meets the minimum: it says what is inspected and how it runs. But because there is no output schema, the agent gets no signal about the shape of the capability/verification data returned, and "验证范围" (verification scope) is left undefined.

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?

The tool takes zero parameters, so per the rubric the baseline is 4. There is nothing for the description to disambiguate at the parameter level.

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 verb "查看" (view) is clear and the object combines "两站能力、验证范围及运行方式" (capabilities of the two sites, verification scope, and execution mode), which points to a capability/introspection tool. However, "两站能力" is ambiguous — it never states which two sites or what a "capability" record contains, and it is not explicitly distinguished from siblings like check_login or open_login that also probe state.

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?

No when-to-use guidance, no prerequisites, and no explicit alternatives are named. The trailing "无需启动浏览器" implies this is the lightweight alternative to open_login, but that routing is left for the agent to infer rather than stated.

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