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

Annotations already cover the safety profile (readOnly, openWorld, idempotent, non-destructive), and the description adds genuinely non-obvious behavioral facts: scripts and nav are removed, a token estimate is returned, and access is rate-limited to 10 free calls/day then $0.002/call with concrete payment paths (x402 via params._meta or HTTP, or X-API-Key credits). That cost/auth disclosure is exactly the kind of operational context an agent cannot get from 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 action and output shape, followed by the removal rules, then the commercial terms. Dense but every clause carries information; the bracketed host tag is minor filler and the pricing sentence is long, though it earns its place for call planning.

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 an output schema present and full schema coverage, the description needn't explain return values, and it covers the transformation semantics, auth, and rate limits well. The one gap is that no parameters are required, yet the description never states that at least one of url or html must be supplied, or what happens on fetch failure or non-HTML responses.

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 description coverage is 100%, so url, html, and maxChars are already documented, and the description largely restates them. The one small addition is presenting url and html as alternatives, but the schema's own 'or raw HTML (POST)' text already conveys that, so no baseline lift is warranted.

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 pair: fetch a public URL (or raw HTML) and return clean LLM-ready Markdown of the main content. It further enumerates what is preserved (headings, links, lists, tables, code) and what is stripped (scripts/nav), which makes the transformation concrete and clearly distinct from the reverse-direction sibling markdown_to_html.

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?

The description implies usage through the 'public URL (or pass HTML)' phrasing and the 'main content' extraction goal, and it constrains inputs to public URLs. It never says when to choose this over alternatives such as web_read_markdown, nor does it state exclusions (paywalled, JS-rendered, or private URLs), so the agent must infer fit from the name alone.

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