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

Beyond readOnlyHint/openWorldHint the description discloses a crawl budget (the page plus at most two more same-site pages, robots.txt and llms.txt), that it obeys robots.txt, does not run JavaScript, and opens no third-party pages. It also explains the scoring model, that Google listing and page-speed groups are omitted and the remaining groups rescale to 100, and crucially that a missing fact means 'not found in the fetched HTML' rather than absent — a caveat an agent cannot get anywhere else.

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 trigger condition is front-loaded and every clause carries usable information — fetch scope, output shape, scoring, and limitations. The middle portion is dense, heavily comma- and colon-laden prose that takes a careful read to parse, which costs it a point on structure despite near-zero wasted content.

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?

There is no output schema, so the description must define the return value, and it does: fetched facts plus a score out of 100 with group sub-scores and the failing checks ordered by points at stake. Combined with the explicit statement of what it cannot see, an agent has everything needed to call it and interpret results 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% and the single parameter already documents format and the 'not a Google/Yelp/delivery-app page' constraint, so the schema does the heavy lifting. The description reinforces the same scoping ('Pass the restaurant's website address') and implicitly frames the input as the root page that drives the crawl, which adds modest value over the schema.

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 pairs a specific verb with a specific resource (audit a restaurant's own website) and enumerates exactly what it checks: menu with prices, phone numbers, hours, Restaurant structured data, ordering/reservation links, llms.txt, AI crawler blocking. It also draws a clear boundary that separates it from sibling tools like check_restaurant_systems or get_site_index by stating this reads only the website and not listings.

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 opening clause gives a concrete trigger: a restaurant owner or operator asking how their own site looks to customers, search and AI assistants. It also supplies exclusions — only the restaurant's own site, not a Google/Yelp/delivery-app page, and 'does not audit maple.inc'. It stops short of naming which sibling tool to use for listing or systems questions, so the agent must infer alternatives.

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