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

Goes well beyond readOnlyHint/openWorldHint: it discloses exactly which elements are stripped, that div-based cookie banners survive, that blocked pages return 503, and that the call costs $0.002 USDC via x402 with failures uncharged — pricing and failure semantics that no annotation carries.

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 what it returns before qualifying limitations, then pricing last — a sensible order. It is dense but every clause carries information; the only stumbling point is a long run-on sentence combining output shape with removal rules.

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?

Even though an output schema exists, the description still characterizes the return content, the filtering behavior, failure mode, and paid-call mechanics. For a one-parameter extraction tool with a fee, nothing an agent needs before calling is missing.

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?

With one parameter at 100% schema coverage, the schema already documents the url field and its 2048-character limit. The description adds only the constraint that it must be a single public page, which is marginal but real.

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+resource: extract one public https page's <title> and <main>/<article> (else <body>) as Markdown with links and images resolved. It also explicitly names the sibling it is not (agent_intel_html_dom_to_clean_markdown, for raw HTML you already have), so the agent can distinguish the two 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?

Clear context for use — a single public https page, not a batch, not raw HTML — and the alternative is named with its own trigger condition. It stops short of explicit exclusions such as JS-rendered or authenticated pages, and the 503 note only implies which pages to avoid.

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