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

Annotations already declare readOnlyHint=true, idempotentHint=true, and destructiveHint=false, covering safety. The description adds value beyond annotations by revealing that the tool performs a real page load (a behavioral trait likely to have network side-effects), discloses the cost ($0.03 per call), and summarizes the return structure (pass, metrics{}, findings[]), which is not redundant given the output schema exists but is not shown to the model.

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 description is compact: two sentences that front-load the key deliverables (metrics and return format) and the qualification ('not a full Lighthouse audit'). The cost is stated succinctly. No filler words or redundant phrases. Slightly more could be trimmed (e.g., the return summary could be dropped if output schema is visible), but overall it is efficient.

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 a simple read-only tool with one parameter, the description covers the essentials: what it measures, the nature of the operation (real page load), the cost, and the return shape. Nothing critical is missing for an agent to decide whether to call it. It does not address rate limits or potential failures, but those are not implied by annotations or schema, and the tool is straightforward.

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?

The only parameter, 'url', has a schema description that fully covers its meaning and format ('Live, fetchable http(s) URL to audit'). The tool description adds marginal context by noting the page load is 'real', which reinforces the 'live' nature, but essentially replicates the schema. With 100% schema coverage, baseline 3 is appropriate.

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 specific verb ('audit') and resource ('page performance'), enumerates concrete metrics (DOM node count, transferred bytes, request count), and explicitly contrasts with a full Lighthouse audit. This clarifies scope and differentiates from the concept of a comprehensive audit, though it doesn't name sibling tools explicitly.

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 implies this is a lightweight, focused performance check ('not a full Lighthouse audit') and notes a per-call cost, suggesting it is for quick spot-checks. However, it does not explicitly state when to prefer this over sibling tools like audit_bundle or audit_security, nor does it provide any exclusion criteria.

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