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

Annotations already declare readOnlyHint, idempotentHint and destructiveHint=false, so the safety profile is covered. The description adds one genuine behavioral trait beyond that: home preview may return a requiredDecision, prompting a mirror-vs-editable question before structure_* tools. That is useful, but it is unexplained and the return shape otherwise is not described.

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?

It is short and front-loads the core purpose, which is good. But the second clause is compressed to the point of obscurity ('ask mirror vs editable before structure_*'), trading clarity for brevity.

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 an 8-parameter tool with no output schema, the description should explain what the composed-HTML check returns, yet it only hints at requiredDecision for home preview. The assertion params (contains/notContains/selector) and the returned content are not contextualized, leaving the agent under-informed.

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 88%, so the schema documents the parameters (site, context, variant, contains, notContains, selector, guestToken) itself. The description adds no parameter-level meaning beyond what the schema provides, so the baseline 3 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?

The phrase 'Verify-only composed HTML check' names a verb (verify/check) and a resource (composed HTML) and signals it does not mutate, which separates it from edit_page. However, it does not distinguish itself from the sibling verify_page, and the name 'preview' conflicts with the 'verify-only' framing, leaving the exact purpose ambiguous.

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 only usage direction is the cryptic 'ask mirror vs editable before structure_*', which hints at a workflow ordering but never says when to choose preview_page over verify_page or other read tools. No when-not-to-use or prerequisite guidance is given.

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