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

Annotations mark this non-readOnly and non-idempotent, which is otherwise puzzling for a pure text transform; the description resolves that by disclosing the $0.001 USDC charge paid via x402, and 'per successful call' tells the agent failed calls are free. It still omits what authorization/wallet setup the payment requires and any rate or size limits.

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?

Three tight sentences: transformation semantics first, use case second, cost last. Every clause carries information an agent needs and nothing is repeated from the 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?

For a one-input, no-output-schema utility, the description covers behavior, purpose, and cost. The only real gap is failure/edge behavior (invalid or massive HTML, truncation), which an agent might want before invoking on arbitrary fetched pages.

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?

There is only one parameter and schema coverage is 100%, so the schema carries parameter documentation. The description adds nothing about the input (encoding, size limits, whether a full document or fragment is expected), which is the expected baseline for a single-param 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?

Specific verb+resource with concrete behavioral detail ('strip HTML to readable plain text'), plus a breakdown of what the transformation does (scripts/styles removed, block elements become line breaks, list items bulleted, entities decoded). An agent can distinguish it from siblings like markdown_to_html, pdf_text, text_extract, and extract_rendered without opening any 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?

'Use to feed web content or emails to an LLM' gives a clear triggering context and intent. It stops short of naming an alternative or stating when-not to use it (e.g., prefer extract_rendered for JS-rendered pages), so it does not reach the explicit routing bar of a 5.

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