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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so the description does not need to re-establish safety. It does add genuinely useful non-obvious context beyond them: the call is 'Free, no browser session,' meaning it does not consume or open a Cloud Browser session, and it degrades to a general method for uncatalogued apps. Missing only the shape/size of the returned guidance, but with no output schema and cheap cost this is minor.

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 purpose and the enumerated contents are front-loaded, and the call-timing instruction comes early in the second sentence, so the agent gets routing information immediately. It is dense and somewhat list-heavy in the first sentence (which browser, sign-in link, method, screens, menus, actions, notes, dedicated tools), but every listed item corresponds to real returned content rather than filler.

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?

For a two-parameter, read-only guidance tool with no output schema, the description covers what it is, what it returns, when to invoke it, its cost/session behavior, and its fallback for uncatalogued apps. An agent has everything needed to decide to call it and to supply both optional parameters correctly.

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 both parameters (app, task) are documented with a stated default, so the schema carries the baseline. The description still adds meaning beyond it by establishing that the guide is app-agnostic and that an unrecognized app name or slug yields the general method rather than an error, which affects how an agent should fill the 'app' field for unknown targets.

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 names the resource concretely and enumerates what the guide covers: which browser to use for the workspace, the sign-in link, the step-by-step method, the app's screens/menus/actions, notes, and app-specific tools. This clearly separates it from the cotlet_browser_* action siblings, which perform clicks rather than explain them. It stops short of a crisp verb+resource statement ('How to work in an app' is content-shaped rather than action-shaped), so a 4 rather than a 5.

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?

The trigger is explicit and actionable: 'Call it before the first browser step in an app,' which also implies not calling it later in the flow. Coverage is stated too ('Works for any web app; one outside Cotlet's catalog gets the general method'). It does not explicitly name a when-not case or point to a sibling alternative for follow-up steps, so it falls just 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.