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

Adds substantial context beyond annotations: the full return object shape, the 10-action cap, that screenshot returns MCP image content, and the metering model (shared 100/day free bucket, then 3 credits/call over x402). There is mild tension with readOnlyHint=true given form-submit/typing capability, but the framing is interaction-with-a-public-page rather than a state-changing API call, so it is not a direct contradiction. A note on what happens when an action fails mid-sequence would complete it.

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?

Front-loads the core action, then uses labeled 'When to use', 'Do not use', 'Returns', and metering clauses. Dense but every sentence carries operational information; nothing is redundant with the name or title.

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?

Strong for a complex tool with no output schema: it spells out the return fields (ok, url, final_url, title, markdown, chars, elapsed_ms, screenshot?, xhr?, took_ms, _metering), the action limit, and cost. The remaining gap is how per-action error/failure is surfaced within {ok, ...} and what happens if one of the 10 actions fails.

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 all six parameters and their defaults are already documented. The description only restates the 10-action maximum (already in maxItems) and adds that screenshot yields MCP image content; it adds no per-action syntax detail (e.g. selector vs text target for click/type) beyond what the schema hints at.

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 ('drive a real Chromium browser') plus resource ('one public page') and enumerates the interaction primitives: click, type, press keys, scroll, wait for selectors. It explicitly contrasts itself against web_fetch and web_crawl, so the agent can distinguish it from siblings without opening schemas.

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?

Provides explicit 'When to use' (content hidden behind cookie banners, tabs, 'load more', form submit that web_fetch/web_crawl cannot see) and explicit 'Do not use' (plain reading -> web_fetch, bulk crawling -> web_crawl, no login/paywall bypass). This is the when/when-not/alternatives trifecta.

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