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

The annotations already declare readOnlyHint, idempotentHint, destructiveHint=false, and openWorldHint=false, so the safety profile is covered. The description adds non-obvious behavior: the call costs nothing and opens no browser session, and it may return the app's dedicated tools when Cotlet has them, which prepares the agent for the response shape.

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 call trigger are front-loaded in the first sentences, and almost every clause supplies a distinct piece of information the agent needs. The trailing Airalo action list is the least essential part, growing the description for a single-app example, but it still helps route the agent to the airalo_* tools.

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?

For a read-only guidance tool with no output schema, complete and fully documented parameters, the description covers what the response will contain, when to call, and its cost and session behavior. An agent has what it needs to invoke it correctly; only the absence of explicit exclusions keeps it from a 5.

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%, so both parameters are documented, including the default of Airalo. The description adds a small amount beyond the schema by explaining that the app parameter may name an app outside Cotlet's catalog and that the tool then returns a general method, plus enumerating Airalo's covered actions, but it says nothing extra about the task parameter.

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 a concrete verb and resource, saying the tool returns the method for working in an app: which browser to use, the sign-in link, step-by-step actions, screens, menus, notes, and the app's dedicated tools. It also clearly distinguishes this from the cotlet_browser_* action siblings, which perform browser steps, by describing itself as the read-ahead guide called before those steps.

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, and "Works for any web app; one outside Cotlet's catalog gets the general method" sets the scope of that trigger. The description omits when not to call it, for example when the agent already holds the guide, and names no alternative for discovering available apps.

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