net_fetch

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

No annotations are provided, so the description carries the full burden. It discloses automated encoding handling (GBK/GB2312) and the fake_ip behavior with a caution ('谨慎使用'), but it omits critical behaviors such as redirect handling, timeouts, error responses, or the security risks of fetching arbitrary URLs (e.g., SSRF). This is insufficient for a network fetch 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?

The description is two short sentences. It leads with the tool's purpose and follows with the one important usage caution. No filler or redundancy.

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 output schema and no annotations, the description must convey return format and operational details. It only says 'decoded text' without specifying whether it's raw HTML or extracted content, and omits error handling, redirect policies, and rate limits. The tool's potential for misuse (fake_ip) is mentioned but not sufficiently elaborated.

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 schema provides descriptions only for max_chars (33% coverage). The description adds meaning to fake_ip by explaining its effect ('偽装国内 IP') and clarifies the url's purpose implicitly. It does not elaborate on url format or max_chars behavior beyond the schema, but the schema already covers max_chars.

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 directly states the tool's function: '网页抓取/内容采集' (web scraping/content collection) and '抓取 URL 返回解码后的文本' (fetch URL and return decoded text). This clearly identifies the verb, resource, and output, distinguishing it from network utility siblings like net_whois or net_url_status.

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 a general use-case label and a caution for fake_ip, but does not explicitly discuss when to use this tool versus alternatives or any exclusions. No siblings are mentioned, so usage guidance is largely implied rather than explicit.

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