Extract Images Audit

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

It adds meaningful behavior beyond the readOnlyHint: it uses Puppeteer, captures lazy-loaded images, and analyzes specific attributes (format, alt text, srcset, sizing, lazy loading, LCP). It also specifies the output as a 0-100 score with per-image details and recommendations, which aligns with a read-only inspection.

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 sentences, with the core purpose in the first and output/coverage in the second. Every clause adds information without fluff.

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 tool without an output schema, the description sufficiently explains inputs, method (Puppeteer), what it checks, and what it returns (score, per-image details, recommendations). The scope of checks and the lazy-loaded behavior fill in the operational behavior an agent needs to set expectations.

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 describes all three parameters (url, device, timeout) with defaults and constraints, so the description carries no additional parameter-level burden. It doesn't add syntax or format details but none are needed at 100% schema coverage.

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?

Describes the tool as a 'Comprehensive image audit for a web page' with a specific verb (audit) and resource (images on a page). The list of analyses (WebP/AVIF adoption, alt text, srcset, sizing, lazy-loading, LCP) distinguishes it clearly from sibling tools such as check_performance or audit_onpage.

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 first phrase 'Comprehensive image audit for a web page' gives an unambiguous use case, and the detailed analysis list clarifies it is for image-specific investigation. However, it does not explicitly say when to prefer an alternative tool, such as check_performance for overall performance or audit_onpage for general SEO.

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