lighthouse_audit

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

Annotation readOnlyHint=false is consistent with the fact that audits produce report artifacts, so there is no contradiction. The description does communicate what is excluded, but it says nothing about report generation side effects, run duration, or how outputDirPath affects behavior, so it adds only modest context beyond annotations.

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?

Two compact sentences, zero filler, with the capability scope front-loaded before the exclusion and the alternative-tool routing.

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 read/analysis tool with no output schema and a fully documented parameter set, the description covers scope, exclusions, and the alternative tool adequately. Minor gaps remain around what the returned score/report looks like and run-time behavior, but nothing an agent needs to invoke it correctly is missing.

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 100%, so mode, device, pageId, and outputDirPath are already fully documented in the schema (including enum semantics). The description adds no parameter-level information, which is the expected baseline when the schema does the heavy lifting.

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 ('Get') and resource ('Lighthouse score and reports') and enumerates the covered categories (accessibility, SEO, best practices, agentic browsing). It also states what is explicitly out of scope (performance) and names the sibling tool that handles it.

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?

It gives an explicit exclusion and an explicit routing rule: 'This excludes performance. For performance audits, run performance_start_trace.' An agent can select between this tool and performance_start_trace without inference.

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