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

Annotations already establish readOnly, idempotent, non-destructive and closed-world, so the safety profile is covered. The description adds two things the annotations do not: 'Free, no browser session' (no session cost or state created) and an enumeration of what the guide returns, which matters because there is no output schema. It does not say how long the returned method is or whether results are cached.

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 enumeration that carries the purpose, returns, and scope in one breath, which makes it harder to scan than a two- or three-sentence split. The critical instruction ('Call it before the first browser step') arrives second rather than first. Total length is reasonable, but the structure buries the trigger.

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 describing what comes back, and it does list the returned components (browser/sign-in link, step-by-step method, screens/menus/actions, notes, dedicated tools). Combined with the trigger rule and the uncatalogued-app fallback, an agent has enough to call this correctly. Minor gap: no indication of response size or whether the method must be re-fetched per session.

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% — both 'app' (with its Fresha default) and 'task' are documented in the schema, so the baseline is 3. The description adds marginal value by listing the Fresha actions covered ('List appointments, Create appointment, Reschedule appointment...'), which helps an agent judge whether its task falls inside the guide's scope. It adds nothing about how 'task' phrasing affects the response.

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 a knowledge/guidance tool, not a browser action: it returns 'which browser to use for this workspace and the sign-in link, the method step by step, the app's screens, menus and actions, notes, and the app's dedicated tools.' That distinguishes it cleanly from the cotlet_browser_* siblings. The framing 'How to work in an app by clicking in the user's Cloud Browser' is a bit long-winded, but the resource (a per-app playbook) 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?

It gives an explicit trigger: 'Call it before the first browser step in an app.' It also covers the coverage fallback ('Works for any web app; one outside Cotlet's catalog gets the general method'), which tells an agent what happens for uncatalogued apps. It stops short of naming a when-not case or explicitly pointing to cotlet_apps for discovery, so it is not a full routing instruction.

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