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

Annotations already cover the safety profile (readOnly, idempotent, non-destructive), and the description adds cost and side-effect context that annotations cannot express: 'Free, no browser session.' It also discloses the shape of what comes back (sign-in link, method, app screens/menus/actions, notes, dedicated tools), which is valuable with no output schema present. Minor gap: it does not say whether results are cached per app/task or expected to be re-fetched.

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?

Two sentences, but the first is a long comma-separated content inventory that is dense to parse, and the critical instruction ('Call it before the first browser step') is buried mid-second-sentence rather than front-loaded. Nothing is strictly wasted, yet the list could be tightened so the trigger fires first.

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 what the agent gets back, when to call it, and that it costs nothing and opens no session. It leaves slight ambiguity about whether it should be re-called for each new task in the same app. Overall it is complete enough to invoke correctly without opening the schema.

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 baseline is 3, but the description adds real meaning: the 'app' value may be any web app, including ones outside Cotlet's catalog, which receive the general method rather than an error. That clarifies fallback behavior the schema does not. The 'task' parameter's effect on the returned guidance is not elaborated, keeping it out of 5 territory.

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 makes clear this is a retrieval of guidance for operating an app in the Cloud Browser, and enumerates the returned content (browser choice, sign-in link, step-by-step method, screens/menus/actions, notes, app-specific tools). It separates itself from the raw cotlet_browser_* action tools by being the preparatory guide. The opening phrasing 'How to work in an app' reads more like a topic heading than a verb+resource, so it is clear but not maximally crisp.

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 implies once-per-app frequency. 'Works for any web app; one outside Cotlet's catalog gets the general method' scopes applicability so an agent knows a catalog miss is not a failure. It stops short of naming cotlet_apps as the way to discover valid app names, and gives no explicit when-not-to-use.

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