state

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

No annotations are provided, so the description carries the full burden of behavioral disclosure. It does not state whether this is a read-only operation, whether it mutates any state despite being named 'state', what side effects exist, or how the returned array items are structured/ordered. The return signature hints at read-only behavior but nothing is explicitly disclosed about costs, freshness, or scope of the returned data.

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 extremely brief, essentially a one-line signature. It's compact but not informative — underspecification rather than true conciseness. Being short is not itself a virtue when nothing of substance is conveyed.

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?

For a 3-parameter tool with no annotations, no output schema, and no schema description coverage, the description is grossly inadequate. It should explain the meaning of sel, tab, max_items, describe the output format in plain language, and clarify how this relates to other element-tree/inspection tools among the many siblings.

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 0%, and the description provides zero parameter documentation. There are 3 parameters (sel, tab, max_items) and none are explained. The description mentions 'indexed element tree' which may relate to max_items but makes no explicit connection. With 3 undocumented parameters and no compensating description, this is a significant gap.

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 'state() → [{index, changed, tag, text, box}] — 索引元素树' uses a cryptic shorthand. The verb is implied ('get' or 'retrieve') rather than stated, and while it mentions returning element tree indexed items, it doesn't clearly state what operation it performs. The Chinese suffix '索引元素树' (indexed element tree) partially clarifies the return object but the overall purpose is conflated with the return signature rather than plainly stated.

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 guidance on when to use this tool versus siblings like page_html, page_text, get_markdown, or find_text. There's no context provided about what scenario calls for inspecting the element tree state, nor any exclusions or alternatives mentioned. The return-type hint suggests it's an element tree inspection tool but there's no explicit usage direction.

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