fetch_url_content

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

With no annotations, the description carries the full burden and does solid work: it discloses a 5-minute per-URL cache, that redirects are marked with the final URL, that oversized bodies are truncated and flagged, and that auto mode falls back to a headless browser. It omits failure modes entirely — timeouts, non-HTML content, blocked/paywalled pages, or whether the browser fallback has a cost/latency penalty worth avoiding.

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?

Summary sentence is front-loaded and high-signal; the Args block is compact and each entry earns its place. Minor redundancy in restating defaults that also appear in the schema, but with 0% schema coverage that restatement is functional rather than wasteful.

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?

An output schema exists, so return values need not be re-explained; the description still adds the useful note that redirects append the final URL and that truncation is marked. For a 3-param fetch tool the remaining gap is error/edge behavior, which is the main thing an agent would still be guessing at.

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%, so the description must compensate and it does: all three parameters are explained with types, defaults, and behavior (max_chars default 20000 plus truncation-and-marking), and render_mode's three accepted string values are enumerated with tradeoffs despite the schema having no enum. This adds meaning the schema does not provide.

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 opening sentence names a specific verb+resource pair (抓取网页正文, convert to Markdown) and adds differentiating scope: automatic stripping of navigation/ads and Chinese encoding handling. Against siblings search_web and search_github, which locate pages rather than return their content, the tool's role is unmistakable from the description alone.

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?

render_mode guidance is explicit about when to pick each mode (browser for known JS pages to avoid a wasted HTTP round-trip, request for max speed), and the cache rule tells the agent repeat fetches within 5 minutes are cheap. It stops short of exclusions — nothing says when not to use this tool or what happens on non-HTML/auth-gated URLs.

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