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

The annotations already establish readOnly, idempotent, non-destructive, closed-world behavior, so the description only needs to add context. It does: 'Free, no browser session' discloses the cost and side-effect profile that the agent cannot infer from annotations, and it enumerates the content of the reply. It stops short of detailing response format or size.

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-before-first-step rule are front-loaded in the first two clauses, and the two trailing sentences are short and high-value. The middle enumeration ('the app's screens, menus and actions, notes, and the app's dedicated tools') is slightly bloated but each item tells the agent something it will receive.

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 no output schema, the description correctly substitutes a list of what comes back, and with zero required parameters it explains the app default implicitly through the schema. What is missing is any hint about how large the guidance is or how to follow up if the app is unsupported beyond the generic method.

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 'app' (with its Overleaf default) and 'task' are already documented. The description adds one meaningful nuance — that an app outside Cotlet's catalog still works via the general method — but says nothing about how 'task' shapes the output. Baseline 3 applies when the schema carries the load.

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 a specific resource ('how to work in an app') and enumerates exactly what the response contains: which browser to use, the sign-in link, the step-by-step method, screens/menus/actions, notes, and dedicated tools. It also distinguishes itself from the browser_* siblings by framing itself as pre-work guidance rather than an action. It loses a point only because the opening clause is a dense run-on rather than a crisp 'Returns X' statement.

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 'Works for any web app; one outside Cotlet's catalog gets the general method' clarifies coverage breadth. There is no explicit when-not-to-use statement or named alternative (e.g., cotlet_apps for catalog lookup), so it falls short of a 5.

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