audit

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

Annotations already declare read-only, idempotent, and non-destructive, and the description repeats 'Read-only'. It adds useful behavioral details beyond annotations: the output format ('summary line per kind', 'full Markdown report') and the save_to behavior. No contradictions.

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 two sentences, compact and well-structured. It front-loads the core purpose ('One-call page audit'), lists all options efficiently, and includes output details without verbosity.

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?

Given the tool's complexity (5 optional parameters) and the annotations covering safety, the description provides sufficient context: it explains each parameter via schema descriptions and details output behavior. It does not mention edge cases or prerequisites, but the tab_id and scope parameters are self-explanatory from schema descriptions, so nothing critical 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% and each parameter has a helpful description. The main description further enriches parameter semantics by explaining what each kind refers to (e.g., 'resources' means which plugin/theme/module/host slows the page) and clarifying default behavior for kinds like keyboard and css. This goes beyond the schema's enum list.

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 explicitly states 'One-call page audit' and enumerates the exact audit kinds (accessibility, keyboard, SEO, security headers, broken links, Core Web Vitals, unused CSS, resources, cache). This clearly identifies the verb (audit), the resource (page), and distinguishes it from specialized siblings like cookie_audit.

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 says to 'pick the kinds' and lists them, so it's clear when to use this tool for any of those audit categories. It does not explicitly name alternatives or state when not to use it, but the coverage is evident from the kind list, making usage largely implied.

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