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

Beyond the annotations (readOnly/openWorld/non-idempotent/non-destructive), it discloses tab behavior (existing site tab, else a new tab, so the user's own tabs stay) and what comes back ('the elements and text in view, with the same numbers'). It doesn't say what happens on auth failure, session startup time, or pagination/truncation of the returned page content, but it covers the operationally salient behavior an agent needs to sequence the first 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?

Front-loaded with the action ('Starts... and opens `url`'), then the ordering instruction, then tab semantics, then the return value, then the app-specific action list. No filler, and the Productboard enumeration is compressed into a single closing sentence.

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?

For a two-parameter, no-output-schema entry-point tool, the description covers what it does, when to call it, where the URL lands, and what the agent gets back. The only real gap is the absence of explicit contrast with the sibling navigation tool, which would complete the routing story.

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 `app` and `url` are already documented in the schema, including the 'leave it out' guidance for `app`. The description adds only marginal parameter meaning (that the URL lands in the site's open tab if one exists), so the baseline 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?

States a specific verb and resource ('Starts the user's Cloud Browser... and opens `url`'), defines what Cloud Browser is (a real Chrome where the user is signed in), and gives a sequencing rule ('Call it first'). That distinguishes it from the interaction siblings (click, type, read) that presuppose an already-open page.

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, and the app-parameter note tells the agent when to omit it versus when cotlet_app_guide names an app's own Cloud Browser. It doesn't explicitly contrast with cotlet_browser_navigate, so the agent must infer that navigate is for subsequent navigation from an established session rather than for opening the browser.

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