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

Adds behavior the annotations don't cover: no charge when the page can't be fetched and that the tool is paid via x402 with a pointer to list_prices. That pricing/failure-cost context is valuable for an openWorld read tool. Return format is described but failure modes beyond fetch failure (redirects, non-HTML, timeouts) are not.

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?

Three tight sentences: what it returns, when to use it, and cost behavior. Front-loaded with the output shape and no filler.

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?

With no output schema, the description compensates by enumerating the return fields. Read-only semantics, cost model, and the single required argument are all covered, so an agent has everything needed to call it 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?

Single required `url` parameter with 100% schema description coverage, so the schema already defines it as an absolute HTTP/HTTPS URL. The description adds only 'for one URL', which is consistent but not additive. Baseline 4 applies for a one-param tool with full coverage.

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 (returns metadata for one URL) and enumerates the returned fields (title, description, preview image, site name, favicon, canonical URL, OG/Twitter cards). The 'like a chat app's link unfurl' analogy and the 'without reading the whole page' clause separate it cleanly from the read_page sibling.

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?

Gives concrete usage context ('when an agent posts, shares, or summarizes links') and implicitly routes away from read_page by contrasting metadata-only with full-page reading. It stops short of an explicit when-not list or naming read_page directly as the alternative.

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