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

Annotations already declare read-only, idempotent, non-destructive, closed-world, so the description correctly spends no words on safety. It does add genuinely new operational facts the annotations cannot express: the call is free and opens no browser session, which matters for an agent budgeting cost and side effects. It stops short of saying how large the returned guidance is or whether it varies between calls.

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?

The opening sentence is a long comma-chained list, and the purpose verb ("How to work in an app") is buried mid-clause rather than front-loaded. The enumeration of returned sections is useful but reads like an inventory rather than prioritized guidance, and "notes" is vague filler. Nothing is false, but it could be tightened substantially.

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 carries the burden of describing the return payload, and it does so at a section level (browser choice, sign-in, method, screens, actions, notes, dedicated tools). Combined with the call-timing rule and the cost/session note, an agent has enough to decide to call it and knows what it will get back.

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% and the schema already explains both 'app' (name or slug, with a Google Search Console default) and 'task'. The description only implies that guidance is tailored to the named app and confirms any web app is acceptable; it adds no format hints or guidance on when 'task' is worth supplying. Baseline 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?

The description states a specific resource (a per-app guide to driving the Cloud Browser) and enumerates what it returns: workspace browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, and dedicated tools. It implicitly distinguishes itself from the cotlet_browser_* action siblings by being a pre-flight lookup rather than an action, though that contrast is never stated explicitly.

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?

"Call it before the first browser step in an app" is a concrete trigger, and the fallback rule ("one outside Cotlet's catalog gets the general method") pre-empts the main reason an agent might skip it. There is no explicit when-not-to-use case, e.g. whether to re-call it on later tasks in the same app.

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