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

Annotations already declare readOnly, openWorld, non-idempotent and non-destructive, and the description adds real substance on top: the browser is the user's signed-in Chrome, the URL reuses the site's existing tab rather than spawning one, and the call answers with the in-view elements and text. That tab-reuse detail explains the non-idempotent hint in human terms. Failure modes (bad URL, app not enabled) are not covered.

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-loaded with the core action, then tab behavior, then the return content, then the JobAdder routing. Dense but each sentence carries information; the eight-item JobAdder action list is the only passage that runs long, though it does serve a routing purpose.

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 compensates by saying what comes back (in-view elements and text, with the same numbers used later). It also covers session/auth context and the optional app override. Only the app-vs-default decision relies on the agent having read cotlet_app_guide.

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 meaning beyond the schema by explaining the consequence of `url`: it lands in the site's open tab or else a new tab, preserving the user's tabs. The `app` semantics are already fully handled in the schema, so this is a modest lift rather than a full explanation.

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 verb and resource: starts the user's Cloud Browser (a real signed-in Chrome) and opens `url`. 'Call it first' implicitly separates it from the other browser_* steps that operate on an already-open page. It never names cotlet_browser_navigate, though, so the open-vs-navigate boundary must be inferred.

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 a clear ordering rule ('Call it first') and an explicit when-not rule for the `app` parameter: leave it out unless cotlet_app_guide names an app's own Cloud Browser. The JobAdder action list also routes the agent here instead of the jobadder_* tools for those flows. No exclusion is stated for when to prefer navigate on an existing tab.

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