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

Annotations already declare readOnly/idempotent/non-destructive and openWorldHint=false, so the safety profile is covered. The description adds real behavioral context beyond them: it runs no browser session and costs nothing ("Free, no browser session"), and it returns workspace-specific browser and sign-in details. It does not describe return size or format, which is the remaining gap.

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 core routing rule (call before the first browser step) and the scope statement come near the front, and there is no filler. The middle enumeration of returned content is a dense list folded into one sentence, which makes it slightly harder to scan than it needs to be.

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 guide tool with no output schema, the description covers purpose, timing, scope, and the shape of what comes back (method, screens, menus, sign-in link, notes). What is missing is only marginal: no mention of how the response changes when `task` is omitted or how large the guide may be.

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 the two parameters are already documented, and the description does not explain the `task` parameter at all. It does add one piece of meaning the schema lacks: the `app` value tolerates apps outside Cotlet's catalog and falls back to a general method. Baseline 3 for full schema coverage plus that minor addition.

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 states that this returns a per-app playbook for driving a web app in the Cloud Browser, enumerating its contents (browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, dedicated tools). That is enough to separate it from the ~20 cotlet_browser_* action siblings, which do the clicking rather than the planning. The verb is soft ("How to work in an app") rather than a crisp retrieval verb, which keeps it below 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?

It gives an explicit invocation rule: "Call it before the first browser step in an app," which tells the agent exactly where this belongs in a sequence. It also sets scope broadly ("Works for any web app; one outside Cotlet's catalog gets the general method"). It does not name an alternative for the related discovery question (e.g. cotlet_apps for listing apps), so no exclusion guidance.

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