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 genuinely useful non-obvious behavior: "Free, no browser session" tells the agent this call does not consume a Cloud Browser session, which matters when deciding whether to invoke it early. It also discloses the shape of the content returned, though it does not describe the response format or size.

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?

Purpose and the colon-delimited contents list come first, followed by the call-timing rule and scope caveats, so it is front-loaded and each sentence carries information. The middle enumeration is dense and slightly sprawling, but nothing is redundant.

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 takes on the burden of saying what comes back and does so item by item. Both parameters are optional with a stated default, and the tool's role as a pre-step briefing is fully explained, leaving nothing an agent needs before calling 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 coverage is 100%, so both parameters are documented with defaults (app defaults to Ordrestyring) and the task field's intent. The description adds meaning beyond the schema by noting that the app argument still works for apps outside Cotlet's catalog, which clarifies what happens with an unrecognized value. It does not explain how 'task' changes the returned guidance, leaving that mostly to the schema.

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 for working in a given app via Cotlet's Cloud Browser tools) and enumerates exactly what the guidance contains: which browser for the workspace, sign-in link, step-by-step method, screens/menus/actions, notes, and any app-specific tools. This clearly separates it from the cotlet_browser_* action siblings, which perform steps rather than describe them. The opening clause is wordy but the substance is unambiguous.

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" gives an explicit trigger point, which is exactly the routing signal an agent needs against 20 browser_* action tools. It also sets expectations for apps outside Cotlet's catalog (general method instead of app-specific detail). There is no explicit when-not guidance, but the sequencing rule is clear enough to prevent misuse.

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