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

Goes beyond annotations by disclosing the cost mechanism (budgetUsd held while running, then released, making the call free) and an auth requirement ('Needs the write scope'). Annotations already cover the read-only/open-world safety profile, so this supplementary context is a genuine add.

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 dense sentences with the output inventory front-loaded, followed by the operational cost/scope notes. No filler; every clause carries information.

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 an output schema present and 100% schema coverage for the three params (including the viewport enum), the description need not restate return shapes or param syntax. It covers what is read, cost, and auth, which is everything an agent needs to invoke correctly.

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 baseline is 3, but the description adds real meaning: it clarifies budgetUsd is held and released (net free), not a charge, and that the read reflects the visitor's view. Defaults and max repeat the schema but the semantics do not.

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+resource (read a page's visual identity) and enumerates the concrete outputs: heading/body typefaces, palette by role as hex, button radius, logo. This distinguishes it cleanly from siblings like read_page, screenshot_page, and list_page_assets.

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?

Implied context is present ('measured as a visitor sees it', free with a budget cap), but no explicit when-to-use vs alternatives. It never names read_page or screenshot_page as the alternative for the non-style case, leaving selection to inference.

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