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

Beyond the readOnly/openWorld/non-destructive annotations, the description discloses cost accounting ("Uses one capture", remaining captures line), latency and timeout behavior (~30s capture of a partially loaded page), caching semantics for fresh: false, the PDF-as-base64 return quirk, and that ads and cookie banners are stripped. The only notable omission is what happens on failure or refusal (error shape), which keeps it from a 5.

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?

The most decision-relevant facts (what it does, the sibling alternative, cost) are front-loaded, and nearly every sentence carries actionable information. It is dense and slightly run-on in places (return format, cost, and timeout all packed into one block), but no sentence is filler.

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 17-parameter capture tool with no output schema, the description still covers return format (inline image, PDF base64, attached file, trailing quota line), cost, latency, and access restrictions. An agent has everything needed to invoke it correctly on the first try.

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, but the description adds meaning the schema does not: fresh: false ties to a free 24-hour cache and to the returned capture timestamp, as_file is explained in terms of which client apps need it, and format png/pdf implies inline image versus base64 text. This is genuine semantic value beyond the field descriptions.

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 opening states a concrete verb and resource ("See a public web page... Renders the URL in a real browser") and immediately differentiates itself from the sibling extract_content by naming it for text reading. An agent can tell this apart from batch_screenshots or extract_content 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?

Explicit routing guidance is given: use extract_content to read words, device for phone/tablet views, full_page for the whole page, as_file when the app cannot display inline images, fresh: false for a free cached copy. Hard exclusions are also stated (public URLs only; localhost and private addresses refused).

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