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

Annotations already mark the tool as read-only and non-destructive, and the description adds genuinely useful behavioral context beyond that: it converts pages to Markdown, filters boilerplate, and crucially discloses that the tool is paid in USDC on Base. The payment disclosure is important for an agent deciding whether invocation has cost implications. No contradiction with annotations exists.

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 compact: three sentences cover use case, output, exclusions, and payment. It is front-loaded with the primary trigger condition. Minor redundancy exists between 'without wasting context tokens on... boilerplate' and 'optimized for LLM context windows', but no sentence is wasted.

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 description provides enough context for an agent to select and invoke the tool correctly: purpose, target URLs, exclusions, parameter format, and cost. The presence of an output schema means return-value documentation is handled elsewhere. It does not discuss rate limits or edge cases like JavaScript-heavy or authenticated pages, but this is not a critical gap for a simple single-URL converter.

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?

With only one parameter and 100% schema description coverage, the schema already documents the url parameter thoroughly ('Full http(s) URL of the webpage to convert to Markdown'). The tool description restates the general conversion behavior but adds little new parameter-level detail beyond the schema. A baseline score of 3 is appropriate because the schema carries the burden.

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 specific verbs ('parse', 'converts') and clearly identifies the resource: any URL becomes clean Markdown optimized for LLM context windows. The explicit mention of stripping ads, scripts, navigation, and boilerplate distinguishes it clearly from generic fetchers or URL tools. There is no ambiguity about what the tool accomplishes.

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 explicitly states when to use the tool: for parsing clean webpage article content or preparing a URL for summarization. It also gives clear negative guidance by warning against raw API endpoints and binary files such as PDFs and images. These when/when-not signals are sufficient, especially since none of the sibling tools overlap with this functionality.

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