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

Annotations already declare readOnlyHint, idempotentHint, non-destructive, and openWorldHint=false, so the safety profile is covered structurally. The description adds two things annotations can't express: "Free, no browser session" (no cost or session consumed) and the graceful degradation to a general method for apps outside the catalog. It stops short of describing the shape or size of the returned guidance.

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?

Roughly four sentences, with the when-to-call instruction placed late but prominent. The opening sentence is a long comma-spliced list of deliverables that is dense but every clause carries information about what the caller receives; little is genuinely wasted, though it could be split for scannability.

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 must tell an agent what comes back, and it does: browser selection, sign-in link, step-by-step method, UI map, notes, and available dedicated tools. Combined with the explicit call-timing and the free/no-session note, an agent has everything needed to use it correctly in a browsing workflow.

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 Quinyx default, so a baseline of 3 applies. The description adds only indirect meaning — that the app drives whether a catalog-specific or general guide is returned — and says nothing about how `task` shapes the output beyond restating the user's intent.

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 (guidance for working in an app inside the Cloud Browser) and enumerates what it returns: browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, and dedicated tools. It is clearly distinct from the granular cotlet_browser_* siblings, which perform individual page actions, but the opening phrasing is more of a scope statement than a crisp verb+object.

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 point, and "Works for any web app; one outside Cotlet's catalog gets the general method" sets the fallback behavior. An agent knows exactly when to invoke this versus going straight to a cotlet_browser_* action.

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