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

Excellent behavioral disclosure beyond annotations. Annotations cover readOnly and idempotent, but the description adds critical operational details: 200KB HTML cap, 8s timeout, private targets blocked, 422 no-match responses, no charge for errors, untrusted content warning, and pricing ($0.015 via x402, USDC on Base). This is rich context that annotations don't provide.

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?

Very dense and front-loaded, packing a lot of information into a short paragraph. Every sentence serves a purpose (usage, modes, return shape, limits, error handling, security, pricing). It's efficient and well-organized, though the density might require careful reading.

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?

Comprehensive for a web-scraping tool with no output schema. Covers return format explicitly (title, description, canonical, language, links, images, headings, jsonLd, textSample), limitations (caps, blocked targets), error handling (422, no charge), security warning (untrusted content), and pricing. An agent has everything needed to call this correctly.

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%, so the baseline is 3. The description goes beyond the schema by explaining the fields parameter's structure (name to CSS selector, max 20), its behavior (unmatched fields are null with fieldErrors), and that no-match means no charge. It adds practical meaning, though the schema already documents most parameters thoroughly.

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: 'Web scraping to JSON fields.' This is clear and distinguishes it from the sibling 'fetch' by emphasizing structured extraction into named fields. However, it doesn't explicitly contrast with 'fetch' or 'http', leaving some ambiguity about when this is better than those siblings.

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?

Provides clear usage context: 'Use when you need specific data from a page.' Also distinguishes GET vs POST modes. It doesn't explicitly name alternatives like 'fetch' or say when NOT to use this tool, but the context is clear enough to guide selection.

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