page_text

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

With no annotations provided, the description carries the full burden, but it only states what the tool returns. It doesn't disclose whether this triggers network activity, whether it requires a loaded page, or how it handles dynamic content. However, '可见文本' reasonably implies a read-only operation returning rendered text, so the behavioral profile is at least somewhat transparent despite minimal disclosure.

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 a single, compact line: 'page_text() → 可见文本'. It states the function signature and its purpose with zero wasted words. Perfectly concise for a parameterless tool.

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 zero-parameter, no-output-schema tool, the description is reasonably complete. It conveys that the tool returns visible text. Given the simplicity of the tool (no params, no output schema), the minimal description covers the essential contract. It could mention edge cases (e.g., empty page) but for this complexity level, it's adequate.

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 has 0 parameters, so there is nothing for the description to add beyond the schema. With zero parameters, the schema itself is complete and the description needs no parameter elaboration. This satisfies the baseline-4 rule for zero-parameter tools, and since the description clarifies the output is visible text (not raw HTML), it earns a 5.

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 'page_text() → 可见文本' clearly states the tool returns visible text from a page. The verb 'page_text' plus '可见文本' (visible text) specifies it retrieves the rendered text content of the current page. It distinguishes itself from sibling tools like page_html (which returns HTML markup) and get_markdown (which returns markdown).

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 description gives no guidance on when to use this tool versus alternatives. There's no mention of when to prefer page_text over get_markdown, page_html, or find_text. The context (returning visible text) is implied but no explicit context or exclusions are stated.

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