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

Beyond the annotations (readOnly, non-destructive), the description discloses the entire processing pipeline, cost per call ($0.02), payment method (x402/USDC), and constraints like 'no browser, no LLM, no API key'. This adds significant behavioral context and is fully consistent with 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?

The description is a compact, front-loaded paragraph. Every sentence earns its place—process explanation, constraints, cost, and payment. No fluff, and it fits the tool's actual complexity.

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?

The tool is simple, and the description covers the full workflow, output format ('one dataset row per chunk'), constraints, and cost. Despite no output schema, the description compensates by describing what the result looks like, making it complete for an agent to invoke 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 description coverage is 100%, so the parameters are already well-documented. The description adds minimal extra meaning beyond 'Give it a domain' for the items parameter, but the schema already explains both items and maxConcurrency. Baseline 3 is appropriate.

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?

The description uses a specific verb chain ('reads the sitemap, fetches the pages, strips them to clean text and splits everything into ~1000-char chunks') and clearly identifies the resource (domains) and purpose (RAG dataset building). It distinguishes itself from siblings like url-to-markdown by focusing on whole-site sitemap crawling and chunked output.

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 clearly implies usage for building vector-store-ready datasets from a website's sitemap. It mentions what the tool does not require (browser, LLM, API key), which helps set expectations, but it does not explicitly name alternative tools or state when not to use it. Still, the context is strong enough.

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