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 new behavioral facts the annotations cannot express: the call is 'free' (no cost to the balance, relevant given the cotlet_balance sibling) and consumes 'no browser session,' which tells the agent it can call it speculatively. It does not say whether the returned guidance can go stale or needs re-fetching per task.

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 instruction is front-loaded in the first two clauses, but the middle is a long comma-spliced inventory ('the method step by step, the app's screens, menus and actions, notes, and the app's dedicated tools') that is harder to scan than a short bulleted list would be. Nothing is strictly wasteful, but the run-on packaging dilutes the trigger sentence that matters most.

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 saying what comes back, and it does so by enumerating the guide's contents, plus it explains the out-of-catalog fallback. Combined with annotations covering read-only safety, an agent has enough to call it correctly. Minor gap: no indication of whether guidance is keyed to the task argument or is static per app.

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 description coverage is 100% and both parameters (app and task) are documented in the schema, so the baseline of 3 applies. The description reinforces the app dimension ('which browser to use for this workspace', 'the app's dedicated tools') but never mentions the task parameter, so it adds little interpretation beyond 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 names a specific resource (a guide for working in an app through Cotlet's Cloud Browser tools) and enumerates what it returns: which browser/sign-in link to use, the step-by-step method, screens, menus, actions, notes, and dedicated tools. It is distinguishable from the cotlet_browser_* siblings because it dispenses guidance rather than performing a browser action. It loses a point only because the opening phrase 'How to work in an app' is circular before the payoff clause lands.

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 condition, which is exactly what an agent needs to sequence this ahead of cotlet_browser_open/click. 'Works for any web app; one outside Cotlet's catalog gets the general method' sets fallback expectations. It stops short of naming cotlet_apps as the alternative for discovering whether the app is in the catalog at all.

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