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

Annotations already declare readOnly/openWorld/idempotent/non-destructive, and the description adds genuinely new behavior: redirects are followed and re-checked, nav/footers/scripts are stripped, links are made absolute, and non-HTML content types are passed through unchanged. It also discloses the x402 payment requirement ($0.01 USDC on eip155:8453), which is critical operational context absent from annotations. It omits truncation behavior and failure modes.

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, then layered with processing details and the price. Dense but each clause carries information; only the heading/word-count enumeration is slightly listy.

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?

No output schema exists, so the description must describe returns - and it does, naming title, description, language, canonical URL, headings and word count. Payment, redirect and cleaning behavior are covered. The remaining gap is truncation/maxChars behavior and error handling for unreachable or non-public URLs.

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 only 25% (only 'mode' is documented), so the description needs to compensate. It partially does - 'main/article content first' and 'navigation/footers/scripts removed' explain the main vs all tradeoff, and 'plain-text and JSON responses are returned as-is' hints at format behavior - but maxChars is never mentioned and truncation semantics are left entirely undocumented.

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 ('Fetch a web page') plus the exact output shape (clean main text, Markdown, title, metadata), which distinguishes it from pure converters like html_extract. It does not explicitly say how it differs from web_metadata or web_links, which overlap on the metadata portion.

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 ('Fetches a public URL') and names an implicit constraint (public URLs only, paid per call), but gives no when-to-use/when-not guidance relative to siblings such as html_extract (for HTML you already have) or web_metadata. The agent must infer the alternative.

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