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

Annotations only cover readOnly/openWorld; the description adds the material behavior an agent cannot infer: a $0.005 USDC x402 charge per call, the exact failure mode without payment (returns payment requirements), and the three ways to satisfy it (X-PAYMENT header, PAYMENT-SIGNATURE header, params._meta["x402/payment"]). It also discloses what gets removed before conversion and what the returned chunks contain.

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 action, then output shape, then cost, then payment recovery — a sensible priority order with little filler. The opening fragment 'POST HTML or a public URL' is slightly clipped, but every sentence carries actionable information.

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 does the necessary work by enumerating chunk contents, and it fully explains the non-obvious payment handshake. Remaining gaps are the url-vs-html exclusivity and chunk/overlap defaults, which matter for correct invocation but are narrower than the coverage it already provides.

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 50%: url and html are documented, but chunkTokens and overlapTokens have no schema descriptions. The description only gestures at them via 'token estimates' and 'configurable overlap' — no defaults, units, ranges, or interaction rules — and it does not say that url and html are mutually exclusive alternatives, which is the key calling constraint for a 0-required-parameter tool.

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 transformation chain: takes HTML or a public URL, strips scripts/styles/nav/footers, converts to Markdown, and returns heading-aware chunks. The output artifacts (heading paths, token estimates, stable hashes, overlap) plus the RAG framing clearly separate it from sibling converters like url_to_markdown and sitemap_to_markdown.

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?

'For embedding and RAG pipelines' indicates the intended context, and the payment section gives explicit retry instructions. However, it never names a sibling (url_to_markdown, sitemap_to_markdown, page_structured_extract) or states when to prefer this chunking tool over a plain Markdown conversion, leaving the choice to inference.

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