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

Annotations already declare readOnly/idempotent/non-destructive, so the bar is lower, and the description adds two facts not in the annotations: it is free and consumes no browser session. It also makes clear the response is instructional content rather than an action performed on the page. It does not say whether the guidance can go stale or how long the returned method is.

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 when-to-call instruction are front-loaded, and the enumerate-what-you-get clause earns its space because there is no output schema. The first sentence is an overlong comma-list that is denser than it needs to be, but there is no filler or repetition.

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 does the necessary work of enumerating the returned content (browser choice, sign-in link, step-by-step method, screens, menus, actions, notes, dedicated tools) so the agent knows what to expect. It also covers the out-of-catalog case and the calling cadence, which are the main uncertainties for a two-optional-parameter guidance 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% and both parameters are documented in the schema, including the Recruiterflow default, so the baseline of 3 applies. The description adds only indirect meaning: 'which browser to use for this workspace' hints at what the app parameter resolves to, and the catalog note implies non-standard app names still work, but neither parameter is explained beyond schema text.

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 states specifically that this returns operational guidance for driving an app in the Cloud Browser: workspace browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, and any dedicated tools. That is concrete enough to separate it from the cotlet_browser_* action tools, though it never names a sibling explicitly and the opening phrase 'How to work in an app' leans on the title rather than a crisp verb.

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 a clear trigger point and implicitly caps usage to once per app. The catalog fallback ('one outside Cotlet's catalog gets the general method') tells the agent it need not pre-check app availability. It stops short of naming alternatives such as cotlet_apps for discovery or warning against repeated calls mid-task.

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