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 genuinely new behavioral facts beyond them: 'Free, no browser session' tells the agent there is no cost and no Cloud Browser session is opened or left dangling. It does not describe the shape or length of the guidance returned, but the extra cost/session disclosure is the most operationally important part.

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?

It is one dense but economical sentence followed by two short clarifying clauses, and the trigger ('Call it before the first browser step') is placed near the end rather than front-loaded. Nothing is redundant, though the long colon-delimited list of returned content would read better split into a return-value line.

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 describing the return payload and does so reasonably ('the method step by step, the app's screens, menus and actions, notes'). For a 2-optional-parameter, read-only guidance tool in a large browser-automation toolset, that is close to complete; only the fallback behavior for unknown slugs and whether results vary by `task` remain unstated.

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 both `app` (including its 'Default: Agile CRM') and `task` described in the schema, so the agent already knows the syntax. The description only gestures at parameters indirectly by mentioning the workspace's browser and app-specific tools; it adds no meaning about how `app` accepts slugs vs names, nor how `task` shapes the returned method. Baseline 3 is appropriate when the schema does the work.

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 enumerates what the tool returns (which browser for the workspace, sign-in link, step-by-step method, screens/menus/actions, notes, app-specific tools), so an agent can tell this is a guidance-lookup tool rather than an action tool. It is not a tight verb+resource statement — 'how to work in an app' is nominal — and it never names its nearest sibling cotlet_apps directly, only alluding to 'Cotlet's catalog'.

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 clarifies coverage ('Works for any web app; one outside Cotlet's catalog gets the general method'), which prevents the agent from thinking an uncatalogued app means failure. It stops short of stating when not to call it (e.g., do not repeat within the same session) or naming alternatives for pre-browser exploration.

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