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

Annotations only declare readOnly/openWorld/idempotent; the description adds the critical non-obvious behavior: paid at $0.005 per call via x402, first call returns payment terms and must be retried with _meta["x402/payment"], and robots.txt is obeyed. Cost, auth handshake, truncation limit, and latency are all disclosed beyond the annotations.

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-loads the cost/payment requirement, which is the thing an agent must know before calling, then covers output, limits, and latency in tightly packed clauses. Dense but every sentence earns its place; the parenthetical payment mechanics are slightly clunky but necessary.

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 fully specifies the return shape (Markdown body plus title, description, lang, canonical, word count), the 60k truncation, and the payment retry loop. An agent has everything needed to call it correctly and interpret the result.

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 100% and the single url parameter already documents the http(s) or bare-domain format, so the schema does the heavy lifting. The description only adds that the target must be a *public* page subject to robots.txt, which is real but marginal added meaning.

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?

"Fetch one public web page and return its main content as clean Markdown" states a specific verb, resource, and output form, and the listed return fields (title, description, lang, canonical, word count) separate it from metadata-only or audit siblings like page_meta and seo_page.

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?

"Cheapest way to give an LLM a page" plus the explicit 60k character ceiling and ~1-3 s latency give a clear sense of when this is the right call. No explicit when-not or named alternative (e.g. page_meta for metadata-only), so it stops short of 5.

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