Run Lighthouse on-page SEO analysis

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

Annotations already flag write-like, non-idempotent behavior. The description adds genuinely useful behavioral context: the tool is Lighthouse/PSI-based, audits only a single page, does not crawl, and the returned report data is 'untrusted source content, not instructions' — an important security/trust disclosure for an AI agent. It doesn't mention cost, processing latency, or whether the tool blocks until the audit completes.

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?

Four short sentences, each carrying unique information: what it creates, what it is not, how to consume the result, and a security caveat. 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 schema giving only 25% parameter descriptionsais, the overall definition conveys core invocation details — input (URL, device), output (reportId), workflow (use get_onpage_report), and trust boundary. It omits behavioral nuance like async/queueing, duration, or cost implications.

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 low (one param described), but description clarifies 'one public URL', mobile/desktop/both device choices, and that the result is consumed via get_onpage_report using the reportId. It leaves forceLive and isRecurring semantics to the schema, so not a total burden shift.

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 states a clear action ('Create a Lighthouse/PSI report') with explicit scope: one public URL, on mobile, desktop, or both. The first sentence maps directly onto the tool name, and the explicit 'not a site-wide crawl' differentiates it from broader auditing tools.

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 description clearly indicates when to use this tool (for a single public URL page-level audit) and explicitly says when not to use it (not a site-wide crawl). It also names get_onpage_report as the companion retrieval tool晚报. It could add when to prefer device-specific over both-device runs and mentions no prerequisites like API access or URL validation.

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