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 safety profile is covered. The description adds genuinely new behavioral facts: no browser session is consumed and no cost is incurred, and it degrades gracefully to a general method for uncatalogued apps. It does not say anything about response size, latency, or how the returned guidance should be applied.

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?

Substance is present but delivered as a single long colon-list with a tangled lead clause, so the key instruction ('Call it before the first browser step') is buried in the middle rather than front-loaded. Tightening the first sentence and moving the call trigger up would materially improve scanability.

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?

There is no output schema, and the description does the work of explaining what comes back (browser choice, sign-in link, method, screens/menus/actions, notes, dedicated tools), which is what an agent needs before committing to a browser workflow. Given only two optional parameters and rich annotations, the definition is close to complete; only the role of 'task' in shaping the result is unaddressed.

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% with only two optional, well-documented parameters (app name/slug with an Acumatica default, and free-text task), so the baseline is 3. The description adds one useful hint — the app need not be in Cotlet's catalog — but never explains how 'task' shapes the returned guidance, which is the one semantic an agent would want clarified.

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 (a per-app working guide) and enumerates its payload: which browser to use for the workspace, the sign-in link, step-by-step method, screens/menus/actions, notes, and dedicated tools. An agent can tell this is a guidance-retrieval tool rather than an action tool, though the opening clause 'How to work in an app by clicking in the user's Cloud Browser' reads like an action verb and is slightly misleading about what the call itself does.

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 clear trigger ('Call it before the first browser step in an app') and a coverage rule ('Works for any web app; one outside Cotlet's catalog gets the general method'), plus the cost/state note 'Free, no browser session'. It does not explicitly route against the closest sibling, cotlet_apps (the catalog listing), leaving the agent to infer which to call first.

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