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

Annotations already mark readOnlyHint=true and destructiveHint=false, so the agent knows it's safe. The description adds value by explaining that values defined in CSS variables are returned resolved to the hex actually painted, and that it runs in a real browser, which are non-obvious behavioral details. It doesn't go into rate limits or auth, but for a read-only tool this is solid.

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, dense with information, no fluff. The first sentence states what it does and what it returns; the second clarifies an important technical detail about CSS variables. Every word earns its place.

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-only inspection tool with one parameter, this is complete. It sets expectations about the output (design tokens), the environment (real browser), and the edge case (CSS variables resolved). Nothing critical is missing for an agent to decide whether to call it.

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 covers the single 'domain' parameter well (100% coverage). The description reinforces that it accepts a domain like 'stripe.com' and a full URL also works, which adds a bit beyond the schema's example. It could be argued to be a 3, but since there's only one param and the description disambiguates the input format, it edges to a 4.

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 clearly states it reads a site's design system from computed styles in a browser, and goes beyond a generic label by itemizing what is returned: role colors with contrast ratios, type scale, corner radius, and button styling. It differentiates itself from siblings like 'screenshot' or 'scrape' by specifying it's about design tokens even though those siblings aren't named, the distinctive focus on computed CSS variables makes it stand out.

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's clear the tool is for inspecting a site's design system, not for taking a screenshot or extracting content. It mentions it runs in a real browser and resolves CSS variables, implying it's for accurate read-only style inspection. However, it doesn't explicitly state when not to use it, like when a simple screenshot suffices, nor name an alternative sibling like 'extract' for data extraction.

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