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

Annotations only declare readOnlyHint and openWorldHint; the description goes well beyond by disclosing JavaScript rendering in a real browser, a 50,000 character cap, per-page pricing over x402, that failed/empty pages cost nothing, and that omitting payment yields a quote. These are exactly the operational facts an agent needs and none are in the structured fields.

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 the core capability and organized under clear labels (When to use, Use instead, Parameters, Returns), so it scans well. It is dense with pricing and constraint detail, but nearly every sentence carries decision-relevant information rather than 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?

With no output schema, the description compensates by spelling out the return fields (title, final_url, text, text_length, truncated) and the truncation limit. Pricing, free-tier, failure-cost and JS-rendering behavior are all covered, leaving no material gap for calling the tool correctly.

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 real constraint meaning: url must be absolute http(s), public, with no logins and no private addresses, and it explains the payment/quote round-trip beyond the schema's one-line note. It stops short of 5 only because the parameter notes largely restate and lightly extend the schema.

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 ('Read any public web page') and immediately defines the output ('visible text... navigation and boilerplate stripped, plus the title and final URL after redirects'). It differentiates itself from the many siblings by naming the exact output form and the JS-rendering behavior, so an agent can distinguish it from read_pages, page_brief, pdf_to_text and screenshot_page 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?

Has explicit 'When to use' and 'Use instead' sections naming the alternative tool and the condition that selects it (read_pages for 2-5 URLs, page_brief for summaries, pdf_to_text for PDFs, screenshot_page for appearance, attest_page for proof). Nothing is left to inference.

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