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

Annotations already cover read-only, non-destructive, open-world fetching. The description adds value beyond that: it discloses the return shape (weighted signals plus a 0-100 score) and, importantly, calibrates confidence with 'Signals, not proof' so the agent doesn't treat findings as definitive. It does not mention fetch cost, timing, or failure modes for unreachable pages.

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, front-loaded with the core purpose, followed by a compact signal inventory and a one-line caveat. The long enumeration is long but earns its place by telling the agent what qualifies as a hit; the only waste is that it could be grouped rather than listed serially.

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 no output schema, the description correctly supplies the return shape and a confidence caveat, which is what an agent needs to call and interpret this tool. The remaining gap is compareUrl's semantics, which live only in the schema.

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 100%, so both parameters are already documented in the schema. The description adds only the notion of a live page to read and says nothing about compareUrl's diff behavior, so the schema does the heavy lifting and the baseline of 3 applies.

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?

States a specific verb ('look for') and a precisely scoped target ('the default AI-generated design look in a live page's markup and CSS'), then enumerates the concrete patterns detected. This is unmistakably different from the sibling accessibility, contrast, and copy-lint 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 implies the context of use (a live public page, markup + CSS) and warns the output is 'signals, not proof', which guides interpretation. But it never names an alternative sibling (e.g. audit_page_accessibility, lint_design_feedback) or states when NOT to reach for this tool.

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