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

Annotations already declare readOnly/idempotent/non-destructive/openWorld=false, so the safety profile is covered. The description adds behavior the annotations cannot express: 'Free, no browser session' tells the agent this consumes no credits and does not open a Cloud Browser session, which is materially useful when deciding whether to call it before a paid browser step. It does not describe the shape/length of the returned guide, but that is a minor omission.

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?

Front-loaded with the core purpose and then scoped with short, high-signal sentences about when to call, coverage, and cost. The first sentence is an overlong colon-list of contents, but each listed item does tell the agent something about the guide's value, so little is wasted.

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 two-optional-parameter, read-only, no-output-schema guidance tool, this covers purpose, trigger timing, universality, and cost. The remaining gap — how large or structured the returned guide is, and whether it should be re-fetched per task within the same app — is not stated.

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 (app, task) are fully documented in the schema, including the 'Default: Discord' behavior. The description adds no parameter-level meaning beyond the schema — it never mentions that app can be a slug or that task should be phrased in the user's words. Baseline 3 applies when the schema carries the weight.

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 clearly establishes this as a guidance/knowledge tool that returns instructions on operating an app inside the Cloud Browser, and enumerates what the guide contains (browser choice, sign-in link, step-by-step method, screens/menus/actions, app-specific tools). It is distinguishable from the cotlet_browser_* siblings because it explicitly says it is the thing to read before using them. The verb is implicit ('how to work') rather than a crisp action, which keeps it from a 5.

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 concrete trigger point, and 'Works for any web app; one outside Cotlet's catalog gets the general method' covers the fallback case so the agent knows it is still worth calling for unknown apps. There is no explicit when-not-to-use or guidance on re-calling after a failure, which keeps it below 5.

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