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

Annotations already declare read-only, open-world and non-destructive, so the description correctly focuses on what they don't cover: the browser is the user's authenticated real Chrome session, and the call returns a rendered view of the page ('the elements and text in view, with the same numbers'). It does not warn about persistent session state across calls or what happens if a browser is already open (relevant given idempotentHint=false).

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?

Three short, front-loaded clauses with no filler; the operating instruction ('Call it first') lands early. Placement of the return-value clause at the end is acceptable but slightly compressed given how much it conveys.

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 steps up and characterizes the return ('the elements and text in view, with the same numbers'), and it covers auth identity and page scope. What's missing is lifecycle behavior — re-invocation when the browser is already running, and how the returned numbering relates to later click/find calls.

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% for the single `url` parameter, so baseline is 3, but the description adds a genuine constraint the schema omits: the address must be a Joist page, not just any public http/https URL. That is real meaning added beyond the schema.

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 specific verb and resource ('Starts the user's Joist Cloud Browser ... and opens `url`') and identifies the concrete substrate (a real Chrome signed in as the user), which distinguishes it from the other cotlet_browser_* lifecycle tools and from the Joist data tools.

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 explicit ordering ('Call it first'), an alternative boundary ('use it for what the Joist tools do not cover'), and a scope restriction ('Only Joist pages open'). It does not name specific alternatives from the sibling list (e.g. cotlet_browser_navigate) or say when to avoid browser use entirely, which keeps it 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.