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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint=false, so safety is covered structurally. The description does add two genuinely useful behavioral facts not in the annotations — it is free and consumes no browser session — which matters for an agent planning a costly browser flow. Beyond that it says nothing about the shape or size of the returned guidance, so it is additive but thin.

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 is front-loaded, but the body is a single sprawling colon-plus-list sentence that chains browser choice, method, screens, menus, notes, dedicated tools and then a long Skool action roster. The Skool enumeration is the most useful part yet is the least structured, and some clauses ("notes", "when Cotlet has them") are vague filler. Tightening into two or three sentences with the action list separated would improve it.

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 only two optional, fully documented parameters, no output schema, and rich read-only annotations, the description carries its weight: it establishes when to call, what it returns conceptually, and the cost profile. The remaining gap is that it never hints at how the guidance is delivered (single blob vs. per-step), though that is minor for a read-only lookup.

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%: the app field already documents name-or-slug with a Skool default, and task documents "what the user wants done." The description adds real value only through the Skool action inventory, which tells the agent what task phrasings will resolve for the default app. Baseline 3 is appropriate given the schema already carries both parameter definitions.

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 uses a concrete framing — it is a knowledge/method guide for driving an arbitrary web app through the Cloud Browser, covering which browser and sign-in link to use, the step-by-step method, and the app's screens/menus/actions. That distinguishes it from the action-level siblings like cotlet_browser_click or cotlet_browser_navigate, which perform the steps rather than explain them. It is slightly diffuse because it enumerates many payload items in one breath, but the core purpose is unambiguous.

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 specific ordering rule, which is exactly the guidance an agent needs for a prerequisite-style tool. It also handles the fallback case: any web app works, and one outside Cotlet's catalog still gets the general method. There is no explicit when-not-to-use or a named alternative for looking up app capabilities (e.g. cotlet_apps), so it stops short of full routing guidance.

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