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

Beyond the annotations (readOnly/openWorld, not idempotent) the description discloses three behaviors the structured data does not: the target is an authenticated real browser session, the URL lands in the site's existing tab or a new tab so the user's own tabs are preserved, and the call returns the in-view elements and text. It does not cover failure modes (bad URL, unauthenticated site) or whether the session persists after the call.

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 instruction and the "Call it first" ordering are front-loaded in the first two sentences, which is the right structure. The trailing Workiz action list and the compressed phrase "with the same numbers" are less self-evident and cost a little density, but nothing is redundant enough to cut outright.

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 carries the burden of explaining what comes back and does so at a high level ("the elements and text in view, with the same numbers"). For a two-parameter entry-point tool, that plus the tab-handling and auth context is close to sufficient; only error and session-persistence behavior remain unaddressed.

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 `app` and `url` parameters are already documented in the schema, including the "leave it out" guidance. The description adds only marginal meaning on top — the tab-targeting rule for `url` — and says nothing about `app`, so the baseline of 3 applies.

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 gives a specific verb and resource — "Starts the user's Cloud Browser ... and opens `url`" — and clarifies the execution environment (a real Chrome where the user is already signed in). An agent can distinguish it from tools like cotlet_browser_click or cotlet_browser_read, but it never names the closest-sounding sibling (cotlet_browser_navigate), so the differentiator relies on inference.

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 first" is an explicit ordering instruction that tells the agent when to reach for this tool over the rest of the browser family. It also scopes usage to the Workiz task set (List jobs, Schedule job, Create invoice, Record payment). It stops short of stating when *not* to use it or naming an alternative for cases where a browser is already open elsewhere.

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