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

Goes well beyond the readOnly/idempotent/openWorld annotations: per-URL pricing, 422 on more than 5 URLs (not charged), per-page errors in results, 502 when nothing was read (not charged), 20,000-character truncation, and a 1-5 s typical latency bounded at 20 s. The prompt-injection warning about returned page text is a genuinely useful safety note. Minor deduction only because the free-trial/IP-quota sentence is hard to parse and partially ambiguous.

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, then alternatives, then behavior, pricing, safety, and a docs link — a sensible order with no filler sentences. It is dense and information-rich for a one-parameter tool, with the free-trial clause being the one passage that costs more reading effort than it returns.

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?

Covers cost, batch limits, partial-failure semantics, truncation, latency, and untrusted-content handling, which is everything an agent needs before spending money on a paid open-world call. An output schema exists, so the brief return-shape note is a bonus rather than a requirement.

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% and the single `urls` parameter is already well documented, so the baseline is 3. The description still adds meaning beyond the schema by explaining the consequence of exceeding 5 URLs (422, not charged) and that failures are reported per page rather than failing the whole batch.

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 verb and resource with explicit scope: 'Fetch up to 5 web page URLs to Markdown in one batch call.' It also names the two siblings it is not (fetch_page_contents for 10 URLs in contents API shape, render_page for JavaScript), so an agent can route without opening a 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?

Gives explicit alternatives with the selecting condition: fetch_page_contents when you have 10 URLs in the contents shape, render_page when JavaScript is needed. It also states the hard exclusion 'Static fetch only, no JavaScript' and the 5-URL ceiling, so when-not-to-use is covered as well as when-to-use.

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