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

Annotations already declare readOnly, idempotent, openWorld, and non-destructive behavior. The description adds meaningful context beyond that by detailing the bounded result set (links, headings, Schema.org types, redirect evidence, hashes, provenance) and the 'public website' constraint, which implies no authentication is used. It does not contradict 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 single, information-dense sentence that front-loads the primary action ('Convert and extract') before listing supporting details. Every clause adds value, but its length and packing of many signal types makes it slightly less scannable than a two-sentence structure would be.

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?

For a tool with two simple parameters and a rich output schema, the description covers the core behavior, output format options, and typical use cases. The word 'bounded' hints at limits, and the existing output schema means return values need not be fully restated. Minor omissions like size limits or error cases prevent a 5.

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 0%, so the description must compensate. It indirectly explains the 'url' parameter ('public website URL') and the 'output' parameter ('clean Markdown or readable text'), but it never names the parameters or describes constraints such as defaults or allowed values beyond the semantic hints. This is adequate but not fully compensatory.

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 opens with a specific verb ('Convert and extract') and resource ('public website URL'), then enumerates concrete outputs (Markdown/text, links, canonical and heading signals, Schema.org types, redirect evidence, content hashes, response provenance). This clearly distinguishes it from sibling tools like web.metadata or web.links by emphasizing full extraction into multiple signal types.

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 phrase 'for RAG, research, or agent context' provides clear application context, and the mention of 'clean Markdown or readable text' signals common output needs. However, it does not explicitly name alternative sibling tools or state when not to use this tool, so it falls just short of full exclusionary guidance.

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