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

With no annotations, the description carries the full burden and does well: it discloses the payment requirement ($0.01 USDC on Base at GET /api/scrape) and the critical contract that it returns a payment resource rather than the page content. It stops short of describing the shape of that payment resource or what happens on payment failure.

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?

Front-loaded with purpose and the critical payment/return caveat, then a compact param list. The param recitation is largely redundant with the schema, which is the only wasted space.

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?

No output schema exists, and the description compensates by stating what is returned (the payment resource, not the page) and how to pay. For a 3-param tool this is nearly complete, though the mechanics of completing the x402 payment are left to the agent to discover.

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 the schema already documents url, format and max_chars including defaults and the max bound. The description restates these but adds no syntax or format detail beyond structured fields, so baseline 3 applies.

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 names the specific resource ('any web page') and the output form ('clean, LLM-ready markdown, text or html'), and — crucially — clarifies the non-obvious twist that this tool does not fetch the page but returns the payment resource. That lets an agent distinguish it from siblings like search_web without opening the schema.

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?

It states the context implicitly (you want page content, and it's a paid x402 call), but never states when to prefer this over search_web or any alternative, nor any prerequisites beyond the price. Usage is inferable but not routed.

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