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

Annotations already cover read-only, idempotent, non-destructive and open-world traits, so the bar is lower, yet the description adds genuinely useful operational facts: pricing at $0.005 USDC per successful call via x402 on Solana, and an equivalent HTTPS endpoint. It does not describe failure/refund behavior or output format, but the payment model disclosure is exactly the kind of context annotations cannot carry.

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 purpose is front-loaded in the first sentence and the pricing/endpoint details are compact and useful. The duplicated JSON body fragment costs a few tokens redundantly against a fully documented schema.

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 annotations present and full schema coverage, the description supplies what's missing: payment model, transport alternative, and a no-network guarantee. Only the return shape (a Markdown string, and whether it's wrapped in JSON) is left unstated for a tool with no output schema.

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 the schema already documents every parameter including the 256 KB cap and the default-true link/image flags. The inline body snippet restates html/base_url/extract_main but adds no semantics beyond the schema, and it omits include_links and include_images entirely.

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 (convert HTML string to clean Markdown) and enumerates the output flavors (GFM tables, fenced code, nested lists). 'No fetch' plus the string-input framing cleanly separates it from fetch-based siblings like url_markdown and web_to_text.

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?

'No fetch' is an effective negative cue: an agent holding a URL rather than markup knows to look elsewhere. However, no sibling is named explicitly (url_markdown, readability_extract, format_convert), so routing requires a small inference step.

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