web_open

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

With no annotations supplied, the description carries the full burden and does disclose the most important behavioral trait: the request rides on the user's authenticated browser session, so gated content is visible. It also declares the return shape (title plus plain-text body). It omits whether a tab is opened or reused, whether navigation state is mutated for later web_click/web_type calls, and any timeout or failure behavior.

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?

Two short sentences, zero filler, with the action and return value front-loaded and the authentication caveat immediately after. Nothing is redundant with the schema.

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 two-parameter browser tool with no output schema, the description covers action, return values, and the key authentication behavior, which is most of what an agent needs. The remaining gap is statefulness — whether the opened page becomes the active page for web_click/web_type — which matters for chaining.

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 100%, so both url and maxChars are already documented in the schema, which sets the baseline at 3. The description adds nothing about URL format or the truncation semantics of maxChars (e.g. whether truncation is silent), so it earns no bonus here.

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 states a specific verb and resource (打开一个网址) plus the return payload (页面标题和正文纯文本), so the core action is unambiguous. It does not, however, distinguish itself from the sibling web_read, which by name sounds like it also returns page content — the agent must guess which one applies.

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?

Usage is only implied: the note that it runs through the user's logged-in browser hints that this is the right tool when content is behind authentication, but the description never says when to prefer it over web_read, web_click, or web_search. There are no explicit exclusions or alternatives named.

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