wait_for_load

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

No annotations are provided, so the description carries full burden for behavioral disclosure. It mentions polling document.readyState and no listener leak, which gives some behavioral detail, but it doesn't describe what happens on timeout, whether it throws or returns, what states count as 'loaded', or how the timeout parameter interacts with the polling. For a tool that interacts with browser page lifecycle, this is thin coverage.

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?

At one sentence (with a parenthetical), the description is compact and gets to the point quickly. No filler or redundancy. It's arguably too terse for a 5, but as conciseness goes, it's efficient with its few words.

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?

Given the tool is a browser page-load wait with siblings like wait_for_network_idle and wait_selector, there's meaningful differentiation to convey that isn't present. With no output schema and no annotations, the description should explain return behavior, timeout semantics, and how it differs from related wait tools—none of which is covered. For a single-parameter tool this is doable but incomplete.

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 schema just defines a single optional 'timeout' number with no description. The description shows 'wait_for_load(15)', implying 15 is a default timeout value, which offers some hint about what the parameter means. However, it doesn't state units (milliseconds vs seconds), bounds, or behavior when omitted, so the description only marginally compensates for the schema's silence on parameter semantics.

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 'wait_for_load(15) — poll document.readyState (无 listener 泄漏)' indicates it polls document.readyState, giving some sense of the mechanism, but it never explicitly states what the tool accomplishes (waiting for page load) in clear terms. The parenthetical about 'no listener leak' is a technical nicety but doesn't clarify purpose for an agent; the primary action 'wait for load' remains implicit through the name and the code-like shorthand rather than being explicitly described.

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?

There is no guidance on when to use this tool versus alternatives like wait_for_network_idle, wait_selector, or sleep. The '(15)' defaults and polling mechanism hint at behavior, but no explicit context about when a page-load wait is appropriate or when network idle would be better is provided. Usage context is only implied by the tool name, not spelled out.

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