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

Annotations already declare read-only, idempotent, non-destructive and closed-world, so the bar is lower; the description still adds real operational facts — 'Free, no browser session' — which is exactly the kind of cost/side-effect information an agent needs before deciding to call it. It also enumerates the content returned, which the annotations cannot convey.

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 core directive ('Call it before the first browser step') is placed early and every clause carries information. The opening sentence is a long enumerated list, which is dense but functional; the Setmore action list is mildly redundant with the sibling setmore_* tools but still useful as a coverage signal.

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 correctly takes on the job of describing what comes back (browser choice, sign-in link, method, screens, notes, dedicated tools) and adds cost and timing guidance. What it does not explain is how the optional 'task' shapes the returned guidance, a small remaining gap for a two-parameter orientation tool.

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 already documented with defaults. The description still adds meaning beyond the schema by explaining that the app can be any web app and that apps outside Cotlet's catalog fall back to a general method, clarifying what the 'app' argument actually buys.

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 makes clear this is an orientation/guide-retrieval tool that returns the browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, and any dedicated tools for an app. It is distinguishable from the cotlet_browser_* action tools and the setmore_* tools, though the phrasing 'How to work in an app' restates the title rather than leading with a crisp verb like 'Returns the playbook for...'.

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?

Gives a concrete trigger: 'Call it before the first browser step in an app.' It also sets scope ('Works for any web app; one outside Cotlet's catalog gets the general method'), which tells the agent it need not check the catalog first. No explicit when-not or named alternative such as cotlet_apps, keeping it short of a 5.

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