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

With no annotations, the description carries the full burden and discloses a lot: per-page pricing, up-front quoting, settlement despite skipped pages, the 400-on-unreadable-start error behavior, and the USDC-on-Base no-account/no-API-key model. However, it quotes $0.002 per page while the max_pages schema description says $0.001 — a 2x pricing inconsistency that leaves an agent with conflicting cost data.

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?

Five dense sentences, each earning its place: core behavior, pricing model, failure handling, error semantics, and payment/auth. The core purpose is front-loaded and there is 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?

For a tool with no annotations and no output schema, the description covers the essentials: output format, skipped-page handling, error conditions, and the cost model. The main gap is the response envelope — pages and skipped[] are mentioned, but the overall return container is never described.

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 coverage is 100%, so the baseline is 3; the schema already documents types, ranges, defaults, and the truncation flag for all three parameters. The description adds billing semantics (quoted at max_pages up front, fewer pages still a complete delivery) but repeats the price with a conflicting figure and contributes nothing on max_chars_per_page.

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?

States a specific action ('Crawl one site in one paid call') with a clear resource (one site), traversal rule (breadth-first over same-host links), and output format (clean markdown per page). The 'same extraction as /web/contents' reference situates it against the sibling web tools without confusing it with single-page fetchers.

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 scope — 'one site in one paid call' with same-host breadth-first traversal — gives an agent clear context for when this tool fits: multi-page extraction within a single domain. It does not explicitly name alternatives (e.g., web_contents for a single page) or state when not to use it, so it stops short of full routing guidance.

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