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

Annotations already declare readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds two genuinely useful behavioral facts: it is free and consumes no browser session. Beyond that it does not describe response shape or size, so the added value is real but thin relative to the annotation coverage.

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?

There is no filler, but the content is packed into two dense sentences with a colon-delimited list that is slow to parse, and the first sentence has no main verb. The most actionable instruction ("Call it before the first browser step") is buried mid-paragraph rather than front-loaded.

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 return content, and it does so by enumerating the specific sections the agent will receive. Combined with the explicit call-ordering rule, an agent has enough to invoke it correctly; only re-invocation frequency and response size remain unstated.

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 (app, task) are already documented with defaults and length limits, establishing the baseline of 3. The description only obliquely adds meaning, implying via "works for any web app" that the app value need not be in the catalog. It says nothing about how the task string shapes the returned guidance.

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: guidance on operating an app through Cotlet's Cloud Browser tools, enumerating what it returns (which browser for the workspace, the sign-in link, the step-by-step method, screens/menus/actions, notes, and dedicated tools). It is clearly distinguishable from the cotlet_browser_* action tools, which perform steps rather than explain them. It falls short of a 5 only because the opening clause is a verbless list fragment rather than a crisp statement of the action.

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 gives an explicit trigger: "Call it before the first browser step in an app," which tells the agent exactly where this fits relative to the many browser action siblings. It also covers the fallback case for apps outside Cotlet's catalog. It does not say whether it should be re-called per task or per app, nor does it contrast with cotlet_apps for discovery.

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