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

Annotations already declare readOnly/idempotent/non-destructive/closed-world, so safety needs no restating. The description adds genuinely non-obvious context the annotations do not carry: the call is free and opens no browser session, and out-of-catalog apps fall back to a general method. It does not detail output size or format, but with no output schema the enumeration of contents largely covers that.

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-loads the purpose and then packs the returned content into one compact clause-list followed by two short prescriptive sentences; total length is modest. The middle enumeration is dense and reads as a run-on, which costs a little readability, but there is no filler.

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 must convey what comes back, and it does by listing the browser choice, sign-in link, method, screens, menus, actions, notes, and dedicated tools. Combined with the free/no-session note and the outside-catalog fallback, an agent has enough to call it at the right moment; only the shape/size of the returned guidance is unstated.

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 (app, task) are already fully documented with names, limits, and a default. The description adds a useful implicit hint that the app may be outside the catalog, but does not clarify how to fill 'task' or what happens when it is omitted. Baseline 3 is appropriate.

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?

States a concrete deliverable: guidance on clicking through a web app in the Cloud Browser, including which browser/sign-in link, the step-by-step method, screens, menus, actions, notes, and app-specific tools. That clearly separates it from the cotlet_browser_* action tools, though the phrasing 'how to work in an app' at the front is slightly abstract before the specifics arrive.

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?

Gives an explicit trigger ('Call it before the first browser step in an app') and a coverage statement ('Works for any web app; one outside Cotlet's catalog gets the general method'), which tells the agent when it still applies. It stops short of saying not to call it again mid-task, so re-invocation timing is left implicit.

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