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

Annotations already cover the safety profile (readOnly, openWorld, non-idempotent), and the description adds genuinely new behavioral context: it fetches the live site, a store scan reads up to one extra product page, and the agentic-commerce sub-score is explicitly never part of the 100. The cost/latency caveat about tight loops plus the store-detection trigger condition (two or more of five signals) go well beyond structured data.

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?

Front-loaded with purpose and score composition, then return values, then the conditional sub-score, then usage caveats — a logical order with no filler sentences. It is on the long side and the sub-score detail could be compressed without losing meaning.

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 carry the return contract — and it does: overall score, three pillar scores, access state for 10 AI crawlers, failed checks with fixes, and benchmark comparison. Combined with the latency caveat and conditional sub-score behavior, an agent has everything needed to call and interpret it.

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 a single parameter at 100% schema description coverage, the schema already carries format and constraint detail. The description reinforces that scanning targets the domain root and adds no path/scheme, consistent with the schema rather than duplicating it, so the baseline of 4 applies.

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 (scans) and resource (public robots.txt, llms.txt, sitemap declaration, homepage) and explains exactly what is produced: a 0-100 score across three named pillars. The scope statement distinguishes it clearly from siblings like compare_sites or get_benchmark, which do not perform a live per-domain scan.

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 explicit ordering guidance ("Call this first for any domain") and a clear exclusion ("avoid calling it in a tight loop for the same domain"), which tells the agent when not to invoke it. It stops short of naming compare_sites as the alternative when multiple domains are involved, leaving that routing to inference.

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