列出页面工具（静态发现）

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

Annotations already declare readOnlyHint=true; the description reinforces this with '只读' and adds behavior beyond annotations: results are returned as data and PAGE_NOT_CONNECTED is returned when no bridge exists. This is useful context and does not contradict the annotation.

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 description is front-loaded with the core return value, then gives a focused scenario, workflow, and error case in four short sentences. Every sentence contributes a distinct piece of information, with no filler.

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?

Even without an output schema, the description tells the agent what to expect: a list of tool names, descriptions, and parameter schemas, plus the not-connected error case. Combined with the usage scenario and empty input schema, nothing essential is missing for an agent to select and call 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?

There are zero parameters and the empty schema is fully covered, so there is no input-semantics burden. The description even notes that the returned inventory includes parameter schemas, but adds no input-parameter detail because none exists.

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 opens with a specific verb and resource: it returns the tool inventory (names, descriptions, parameter schemas) offered by the currently bridged page. This clearly differentiates it from call_page_tool, which is described as the follow-up invocation step.

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 explicitly gives a trigger scenario: hosts that do not refresh tools/list after page pairing, making newly exposed page tools invisible, and tells the agent to use list_page_tools first then call_page_tool. It stops short of stating when not to use the tool or comparing against the other siblings, so explicit exclusions are missing.

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